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

    Neuronpedia

    INDEX
    Explanations

    interactions and collaborative efforts in a work or team setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    privation
    -0.15
     Hood
    -0.15
    _HIT
    -0.14
     Nat
    -0.14
    akan
    -0.14
     Tarif
    -0.14
    undef
    -0.13
    antas
    -0.13
    rega
    -0.13
    á»ķ
    -0.13
    POSITIVE LOGITS
     safety
    0.18
    Safety
    0.17
     Safety
    0.16
     Scaffold
    0.16
     scaffold
    0.16
     assistance
    0.15
     Simpl
    0.15
     Protection
    0.15
    _slow
    0.15
    atrix
    0.14
    Act Density 0.162%

    No Known Activations