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

    Neuronpedia

    INDEX
    Explanations

    common verbs related to naming or identification

    oai_token-act-pair · gpt-3.5-turbo

    references to naming or labeling, particularly with the verb "call."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.78
     mathemat
    -0.76
     confir
    -0.64
     compr
    -0.64
    oppable
    -0.63
     captcha
    -0.62
     suscept
    -0.61
    ————
    -0.60
     accomp
    -0.59
     Continued
    -0.58
    POSITIVE LOGITS
    igraph
    1.03
     bullshit
    1.01
     attention
    1.01
    ously
    0.95
    phas
    0.93
     themselves
    0.92
    backs
    0.90
     them
    0.88
     him
    0.86
     forth
    0.85
    Act Density 0.046%

    No Known Activations