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

    Neuronpedia

    INDEX
    Explanations

    terms related to strength and power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.17
    ceased
    -0.15
    icerca
    -0.15
    izon
    -0.15
    .VK
    -0.15
    _lineno
    -0.14
    xc
    -0.14
    layan
    -0.14
    Animated
    -0.14
    stroy
    -0.14
    POSITIVE LOGITS
    holds
    0.27
    -strong
    0.22
     strong
    0.21
    /we
    0.20
     Strong
    0.19
    strong
    0.19
    hold
    0.18
     mẽ
    0.18
    Strong
    0.18
    ,strong
    0.17
    Act Density 0.075%

    No Known Activations