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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AAC
    -0.69
     DIRECT
    -0.67
     USPS
    -0.65
     ACC
    -0.63
     Adjusted
    -0.62
     FedEx
    -0.60
    Reloaded
    -0.60
     horizont
    -0.59
    ************
    -0.59
     Competition
    -0.58
    POSITIVE LOGITS
    espie
    0.95
    ichick
    0.92
    amiya
    0.90
    zynski
    0.89
    verson
    0.88
    aney
    0.85
    igne
    0.84
    ensen
    0.80
    zon
    0.80
    ricks
    0.80
    Act Density 0.131%

    No Known Activations