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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing a perception or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.84
    rouse
    -0.75
    iding
    -0.75
    rient
    -0.73
    venge
    -0.73
    atching
    -0.71
    cum
    -0.70
    orthern
    -0.68
     Industry
    -0.67
    learning
    -0.66
    POSITIVE LOGITS
    rils
    0.81
     plaus
    0.78
     unlikely
    0.78
     contrad
    0.78
    ãĤ¨
    0.75
     uncertain
    0.74
     likely
    0.74
     doubtful
    0.74
    Magikarp
    0.73
     innocuous
    0.73
    Act Density 0.044%

    No Known Activations