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

    Neuronpedia

    INDEX
    Explanations

    actions related to interpersonal conflict and legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MI
    -0.15
    OUCH
    -0.15
     ÑģÑĤо
    -0.14
    ons
    -0.14
     Downing
    -0.14
     Jaw
    -0.14
    xed
    -0.13
    MI
    -0.13
    @
    -0.13
    TY
    -0.13
    POSITIVE LOGITS
    icari
    0.16
    obody
    0.16
    #__
    0.16
    rada
    0.15
    ¾ç¤º
    0.15
    kker
    0.15
    änder
    0.15
    _warnings
    0.15
     further
    0.15
    tility
    0.14
    Act Density 0.441%

    No Known Activations