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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sight" and its variants, alongside words that indicate visibility or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.43
     observers
    -0.43
    enumi
    -0.42
     observer
    -0.42
    위
    -0.41
    ecake
    -0.41
     كومونز
    -0.41
    🔄
    -0.40
    不在
    -0.40
     ele
    -0.40
    POSITIVE LOGITS
     rush
    0.81
     rushing
    0.70
     sight
    0.69
     rushes
    0.64
     rushed
    0.63
     RUSH
    0.60
     '\\;'
    0.59
    ArgsConstructor
    0.58
    rush
    0.58
    Rush
    0.56
    Act Density 0.075%

    No Known Activations