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

    Neuronpedia

    INDEX
    Explanations

    sentences containing reported events or conversations

    oai_token-act-pair · gpt-3.5-turbo

    statements related to personal experiences of trauma and distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understandably
    -0.72
     themselves
    -0.70
    EMS
    -0.67
    asm
    -0.63
    aic
    -0.62
     doubtless
    -0.61
    idges
    -0.61
     evidently
    -0.58
     rarity
    -0.56
     Colleges
    -0.56
    POSITIVE LOGITS
     myself
    1.23
     my
    0.80
     personally
    0.71
     THEM
    0.69
    uminati
    0.67
    compan
    0.67
    aca
    0.66
    ograp
    0.65
    ividual
    0.65
    acan
    0.65
    Act Density 0.758%

    No Known Activations