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

    Neuronpedia

    INDEX
    Explanations

    the word "Needless" followed by another word or phrase which is often irrelevant

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "needless to say" and its variations, indicating unnecessary information or common knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appro
    -0.74
    sand
    -0.70
    schild
    -0.67
    roid
    -0.64
     Zheng
    -0.64
    backed
    -0.62
     adm
    -0.62
    ware
    -0.61
    lain
    -0.61
    sonian
    -0.59
    POSITIVE LOGITS
    uits
    0.90
    cale
    0.81
    aez
    0.80
    ĸļ
    0.74
    uploads
    0.73
    nown
    0.73
    atility
    0.72
    ortun
    0.71
    xus
    0.70
     Osw
    0.70
    Act Density 0.022%

    No Known Activations