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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific events or actions within a context

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional support and interpersonal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''
    -0.85
    âĢ¢âĢ¢
    -0.79
    _.
    -0.78
    ___
    -0.75
    .</
    -0.73
     ÂŃ
    -0.70
    —"
    -0.68
    }.
    -0.68
    ··
    -0.68
    "—
    -0.68
    POSITIVE LOGITS
     independ
    0.78
     NXT
    0.74
     KDE
    0.72
     Whilst
    0.72
     NEO
    0.70
     util
    0.69
     alot
    0.69
     organisations
    0.69
     organising
    0.67
     organis
    0.65
    Act Density 1.331%

    No Known Activations