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

    Neuronpedia

    INDEX
    Explanations

    formal written communication elements such as emails, memos, and letters

    oai_token-act-pair · gpt-3.5-turbo

    references to official documents and communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     idols
    -0.76
     evils
    -0.71
     brakes
    -0.70
    ocrats
    -0.66
    Ps
    -0.66
    reci
    -0.66
    tics
    -0.66
    brids
    -0.66
    acists
    -0.66
     perpetrators
    -0.66
    POSITIVE LOGITS
     statement
    0.79
    statement
    0.77
    yssey
    0.73
    Statement
    0.70
    ederation
    0.67
     behalf
    0.66
    idav
    0.66
    uckland
    0.66
    aran
    0.63
    pared
    0.61
    Act Density 0.216%

    No Known Activations