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

    Neuronpedia

    INDEX
    Explanations

    expressions of shock or surprise in emotional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _FM
    -0.16
    okens
    -0.15
    odyn
    -0.15
    [".
    -0.15
    angi
    -0.15
     éĸ
    -0.14
    á»ĩnh
    -0.14
    éro
    -0.14
    gnore
    -0.14
    év
    -0.14
    POSITIVE LOGITS
     disbelief
    0.27
     jaw
    0.25
     incred
    0.25
     shock
    0.24
     gas
    0.24
    Shock
    0.23
     wonder
    0.22
     Shock
    0.22
     shocked
    0.21
     reactions
    0.21
    Act Density 0.389%

    No Known Activations