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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cerberus
    -0.64
     Thumbnails
    -0.60
     Victorian
    -0.56
    mercial
    -0.54
    ãĥ¼ãĥĨ
    -0.53
     CPC
    -0.52
     Disneyland
    -0.50
     CFR
    -0.50
     Costco
    -0.49
     precursor
    -0.49
    POSITIVE LOGITS
    yna
    0.75
    han
    0.75
    hw
    0.74
    jan
    0.74
    uy
    0.73
    je
    0.73
    aj
    0.72
    ahl
    0.72
    ouk
    0.72
    ifa
    0.72
    Act Density 0.506%

    No Known Activations