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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to individuals, particularly in a context involving major actions or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.85
    pmwiki
    -0.79
     Solitaire
    -0.76
    âĶĢâĶĢ
    -0.75
    nesota
    -0.75
     Tycoon
    -0.74
    wich
    -0.74
    */(
    -0.73
    psons
    -0.72
    itto
    -0.71
    POSITIVE LOGITS
    ylon
    0.72
     Gonzalez
    0.70
     Bash
    0.67
    Phill
    0.64
     Vital
    0.63
     Baird
    0.62
    ocial
    0.62
    wered
    0.61
    cles
    0.61
    rax
    0.61
    Act Density 0.047%

    No Known Activations