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

    Neuronpedia

    INDEX
    Explanations

    negative contractions related to denial or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LES
    -0.16
    uard
    -0.16
    DMI
    -0.16
    gis
    -0.15
    ÂĿ
    -0.14
    les
    -0.14
    524
    -0.14
    sec
    -0.14
    ena
    -0.13
    eval
    -0.13
    POSITIVE LOGITS
     not
    0.52
    not
    0.42
     Not
    0.36
     NOT
    0.33
    Not
    0.32
    't
    0.30
    ’t
    0.30
    	not
    0.30
    .not
    0.28
    NOT
    0.27
    Act Density 0.344%

    No Known Activations