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

    Neuronpedia

    INDEX
    Explanations

    specific phrases indicating certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.84
    tagHelperRunner
    -0.83
     also
    -0.75
    also
    -0.74
     både
    -0.72
     nejen
    -0.71
     >=",
    -0.70
    Also
    -0.70
    InvalidProtocol
    -0.69
     Also
    -0.69
    POSITIVE LOGITS
     semplicemente
    1.01
     simply
    1.00
     simplemente
    1.00
     prostu
    0.98
     simplement
    0.97
    干脆
    0.97
     outright
    0.91
    某个
    0.90
    そもそも
    0.88
     simplesmente
    0.87
    Act Density 0.648%

    No Known Activations