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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names, especially the name "Joel," with varying levels of activation for each

    oai_token-act-pair · gpt-3.5-turbo

    the name "Joel" and related references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hib
    -0.76
    FACE
    -0.65
    dayName
    -0.65
    omething
    -0.63
    iness
    -0.61
     gestation
    -0.60
     interests
    -0.60
    ily
    -0.59
     patiently
    -0.59
    IFIED
    -0.58
    POSITIVE LOGITS
     McH
    1.01
    aquin
    0.92
    owitz
    0.83
    ovic
    0.82
     Castro
    0.81
     Goodman
    0.78
    lein
    0.76
    aqu
    0.76
     Kot
    0.76
     Emb
    0.73
    Act Density 0.028%

    No Known Activations