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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities, particularly those starting with "He"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     off
    -0.54
    aarrggbb
    -0.52
     Chip
    -0.48
     للاسماء
    -0.48
    الإنجليزية
    -0.45
    -0.45
    ın
    -0.44
    znam
    -0.41
    huriyet
    -0.41
    لينكات
    -0.41
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.78
    ()?;
    0.75
     Majefty
    0.74
     pleaſure
    0.71
    =$((
    0.67
    "]);
    0.66
     Diſ
    0.66
    lioz
    0.66
     nôtre
    0.65
     defaultstate
    0.64
    Act Density 0.137%

    No Known Activations