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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data, analysis, reports, or claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.74
    usher
    -0.72
     Tiff
    -0.71
    dict
    -0.69
    lda
    -0.68
    anza
    -0.68
    irlf
    -0.67
    ogun
    -0.66
     Tanks
    -0.66
    hiba
    -0.65
    POSITIVE LOGITS
     bet
    0.66
    alf
    0.66
    âĸ¬âĸ¬
    0.65
    functional
    0.65
    Ò
    0.64
    IBLE
    0.62
    ethical
    0.60
    client
    0.60
    âĸ¬
    0.60
     âĢİ
    0.59
    Act Density 0.001%

    No Known Activations