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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collective action or response to challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGE
    -0.16
    .rs
    -0.15
    _OBJC
    -0.15
    ctal
    -0.14
    #
    -0.14
    IED
    -0.14
    oen
    -0.14
    uisse
    -0.14
    égorie
    -0.14
    oir
    -0.13
    POSITIVE LOGITS
    675
    0.17
    uan
    0.16
    次æķ°
    0.16
    itizen
    0.15
     duty
    0.15
    ismatic
    0.15
    chw
    0.14
    ame
    0.14
    915
    0.14
    allas
    0.14
    Act Density 0.072%

    No Known Activations