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

    Neuronpedia

    INDEX
    Explanations

    names or titles that things are named after

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating names or entities that are named after people or specific things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isphere
    -0.73
    IQ
    -0.73
    urable
    -0.70
    idential
    -0.66
    ctory
    -0.65
    Story
    -0.65
    archy
    -0.64
    utic
    -0.64
    iar
    -0.63
    cellent
    -0.63
    POSITIVE LOGITS
     initials
    0.94
     oneself
    0.90
     someone
    0.77
     deceased
    0.75
     Adolf
    0.72
     slang
    0.72
     something
    0.71
     him
    0.71
     the
    0.70
     Ronald
    0.70
    Act Density 0.214%

    No Known Activations