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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    prominent figures and their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.74
     referen
    -0.68
     thous
    -0.65
    acebook
    -0.61
     undermin
    -0.60
     predec
    -0.58
     fundament
    -0.55
     subscript
    -0.54
     comprom
    -0.54
    ß
    -0.53
    POSITIVE LOGITS
    hus
    0.72
    ank
    0.65
    hov
    0.65
    han
    0.64
    angan
    0.63
    ho
    0.62
    ius
    0.61
    esson
    0.61
    hu
    0.61
    hom
    0.61
    Act Density 0.712%

    No Known Activations