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

    Neuronpedia

    INDEX
    Explanations

    phrases related to endorsements or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to acceptance and inquiries about travel or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctica
    -0.89
    Downloadha
    -0.88
    代
    -0.78
    ĻĤ
    -0.75
     Scotia
    -0.71
    ä¸Ń
    -0.70
    女
    -0.70
    apter
    -0.68
    åĤ
    -0.67
     unnecess
    -0.67
    POSITIVE LOGITS
    ed
    1.85
    ing
    1.49
    er
    1.39
    ers
    1.34
    edin
    1.31
    edIn
    1.30
    ership
    1.28
    edly
    1.18
    s
    1.03
    es
    1.02
    Act Density 0.070%

    No Known Activations