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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements about the current state or condition of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.84
     Reſ
    -0.84
     Jefus
    -0.83
     themſelves
    -0.82
     Majefty
    -0.82
     Chriftian
    -0.79
     Theſe
    -0.79
     houſe
    -0.78
     Houſe
    -0.78
     myſelf
    -0.77
    POSITIVE LOGITS
     possible
    0.75
     habido
    0.71
     snowing
    0.71
     impossible
    0.67
     raining
    0.62
     fallu
    0.62
     time
    0.61
     difficult
    0.59
    possible
    0.59
     unclear
    0.58
    Act Density 0.451%

    No Known Activations