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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "behave" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    markup
    -0.16
    é³´
    -0.16
    ierz
    -0.15
    Ñĥз
    -0.15
    ÏĦιν
    -0.15
    limits
    -0.15
    isse
    -0.14
    anke
    -0.14
     Walt
    -0.14
    alez
    -0.14
    POSITIVE LOGITS
    hra
    0.15
     Cle
    0.14
     Charm
    0.14
    empl
    0.14
    rogen
    0.14
    ĽĦ
    0.13
    uten
    0.13
    uron
    0.13
    _versions
    0.13
    ép
    0.13
    Act Density 0.007%

    No Known Activations