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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases starting with "at" that describe different situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating time or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bard
    -0.76
    dar
    -0.74
    Paris
    -0.74
    IFE
    -0.70
    Sharp
    -0.69
    PI
    -0.69
    ORN
    -0.69
    shi
    -0.68
    mma
    -0.68
    Reviewed
    -0.67
    POSITIVE LOGITS
    etheless
    1.24
    »Ĵ
    0.93
     nonetheless
    0.78
     persists
    0.75
     streng
    0.74
     coerc
    0.73
     persisted
    0.73
     construed
    0.71
     disclaim
    0.67
     beware
    0.65
    Act Density 0.160%

    No Known Activations