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

    Neuronpedia

    INDEX
    Explanations

    references to self-harm and issues related to mental health

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

    criticism, punishment, harassment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.74
     '{@
    -0.55
    :✨
    -0.51
    ⓧ
    -0.46
     ffilmiau
    -0.42
    oredCriteria
    -0.41
    ValueStyle
    -0.40
    GCS
    -0.40
     CanadaChoose
    -0.38
    WebpackPlugin
    -0.37
    POSITIVE LOGITS
     tartalomajánló
    0.42
     Scienti
    0.40
    HomeAsUpEnabled
    0.40
    OrWhiteSpace
    0.39
    entierung
    0.39
    又不是
    0.39
    hors
    0.39
    MigrationBuilder
    0.38
     victor
    0.38
    ifikationer
    0.38
    Act Density 0.305%

    No Known Activations