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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to locations and people

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "alle" and its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.90
    olicy
    -0.86
    ascus
    -0.83
    URES
    -0.78
    oppable
    -0.72
    othal
    -0.70
    abies
    -0.69
    olved
    -0.69
    dfx
    -0.69
    astically
    -0.69
    POSITIVE LOGITS
    tto
    1.09
    ffect
    1.01
    mand
    0.87
    tta
    0.87
    tt
    0.80
    phant
    0.79
    lette
    0.77
    val
    0.77
    bone
    0.76
     Spells
    0.75
    Act Density 0.014%

    No Known Activations