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

    Neuronpedia

    INDEX
    Explanations

    words related to the origin or source of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to origin or source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vil
    -0.71
    Agg
    -0.70
    elcome
    -0.66
    owl
    -0.65
    ¯¯¯¯¯¯¯¯
    -0.65
     eyed
    -0.64
    dain
    -0.64
    anyahu
    -0.64
    incial
    -0.64
    ench
    -0.61
    POSITIVE LOGITS
    ates
    0.90
    uating
    0.79
    uates
    0.78
    ator
    0.78
     origin
    0.77
     originating
    0.76
    waters
    0.74
    ators
    0.74
    translation
    0.73
     Destination
    0.71
    Act Density 0.011%

    No Known Activations