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

    Neuronpedia

    INDEX
    Explanations

    contexts of surprise and emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyphicon
    -0.15
    _COMPILE
    -0.14
    @brief
    -0.14
    agate
    -0.14
    rients
    -0.14
    á»ģn
    -0.14
    amos
    -0.14
    deniz
    -0.14
    ieur
    -0.14
    ribbon
    -0.13
    POSITIVE LOGITS
    uther
    0.15
    ally
    0.15
    289
    0.15
     Perry
    0.15
    ichni
    0.15
    SED
    0.14
    iner
    0.14
    me
    0.14
    âĺħ
    0.13
    kid
    0.13
    Act Density 0.178%

    No Known Activations