Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating personal experiences and expressions of sentiments or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    first-person singular pronouns and their associated verbs expressing personal thoughts, actions, or experiences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     poichè
    -0.40
    transQ
    -0.39
     pleaſure
    -0.39
     zijne
    -0.36
     Shakspeare
    -0.35
     ciertamente
    -0.34
     néanmoins
    -0.34
     regalías
    -0.33
     kekasih
    -0.33
     vervolgens
    -0.32
    POSITIVE LOGITS
     involve
    0.87
     provide
    0.82
     introduce
    0.82
     recognize
    0.79
     promote
    0.78
     verify
    0.78
     translate
    0.78
     apply
    0.78
     combine
    0.77
     decide
    0.77
    Act Density 0.951%

    No Known Activations