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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or insistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SuppressMessage
    -0.76
    postmedia
    -0.71
    IsContent
    -0.67
    InputBorder
    -0.67
     別注
    -0.66
    ñora
    -0.65
    gulier
    -0.63
    regelen
    -0.63
     Ome
    -0.62
     curs
    -0.62
    POSITIVE LOGITS
     insiste
    0.67
    NSString
    0.61
    rungsseite
    0.61
     possess
    0.59
     insisting
    0.58
     anymore
    0.57
     possesses
    0.56
     retrieve
    0.56
     retrieval
    0.56
    Pyx
    0.56
    Act Density 0.063%

    No Known Activations