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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that indicate a hypothetical or suggestion-based context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Toll
    -0.16
    o
    -0.16
    egan
    -0.15
    vo
    -0.14
    peer
    -0.14
    atore
    -0.14
    uish
    -0.14
    bench
    -0.14
    fh
    -0.14
     todd
    -0.13
    POSITIVE LOGITS
    eyin
    0.17
    unny
    0.16
    okus
    0.15
     Premi
    0.15
    ạm
    0.14
    лÑıÑħ
    0.14
    ismu
    0.14
    walls
    0.14
    une
    0.14
    876
    0.14
    Act Density 0.113%

    No Known Activations