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

    Neuronpedia

    INDEX
    Explanations

    terms related to aggressive behavior or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ever
    -0.17
     ROUT
    -0.15
    ambda
    -0.14
    ugen
    -0.14
    lsen
    -0.14
    gon
    -0.13
    eder
    -0.13
    OrCreate
    -0.13
    vez
    -0.13
    iquid
    -0.13
    POSITIVE LOGITS
    imate
    0.15
    THR
    0.15
    yw
    0.14
    -leaning
    0.14
    -gnu
    0.14
     immediate
    0.14
    /fast
    0.14
    acia
    0.14
    ulous
    0.14
    ẩu
    0.13
    Act Density 0.016%

    No Known Activations