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

    Neuronpedia

    INDEX
    Explanations

    terms related to rejection or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    act of rejecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.51
    EndInit
    -0.48
    initComponents
    -0.47
    esModule
    -0.45
    ">//
    -0.44
    IsMutable
    -0.43
    ernalia
    -0.43
    triangleq
    -0.42
     CreateTagHelper
    -0.42
     continúas
    -0.41
    POSITIVE LOGITS
    reject
    2.84
    Reject
    2.16
     reject
    2.08
     Reject
    2.08
     rejecting
    1.80
     rejects
    1.73
     rejection
    1.70
    REJECT
    1.66
     Rejection
    1.58
     rejected
    1.54
    Act Density 0.004%

    No Known Activations