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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or terms, such as "Pattison", "Bridge", and "Lollipop"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or names associated with notable actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holding
    -0.70
     Controlled
    -0.69
    minist
    -0.68
    ptives
    -0.67
     detain
    -0.66
    irc
    -0.65
    GROUND
    -0.65
     forecasting
    -0.63
    ccording
    -0.63
     STATES
    -0.63
    POSITIVE LOGITS
     Patt
    0.88
    aya
    0.82
    idge
    0.79
    enos
    0.78
    ish
    0.76
    ifice
    0.75
    sey
    0.75
    ength
    0.74
    olver
    0.73
    uxe
    0.73
    Act Density 0.016%

    No Known Activations