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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "trigger" and its variants, indicating reactions or responses to situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä½į
    -0.16
    ä¹ħ
    -0.15
    UST
    -0.15
    ugo
    -0.15
    /md
    -0.15
    ake
    -0.14
    ikt
    -0.14
    ties
    -0.14
    ynchronize
    -0.14
    imony
    -0.14
    POSITIVE LOGITS
    -response
    0.18
    63
    0.17
    yen
    0.16
    ivate
    0.16
    æĿIJ
    0.15
    ingly
    0.15
    les
    0.15
    363
    0.15
    znik
    0.14
    pow
    0.14
    Act Density 0.113%

    No Known Activations