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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss or damages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     so
    -0.49
    .
    -0.46
    r
    -0.46
     z
    -0.44
    d
    -0.44
     ja
    -0.44
     ab
    -0.43
    ه‌ای
    -0.42
    y
    -0.41
    </blockquote>
    -0.40
    POSITIVE LOGITS
     autorytatywna
    1.05
     propOrder
    1.00
     Roskov
    0.95
     myſelf
    0.92
     HasFactory
    0.92
    
    0.91
     pleaſure
    0.86
     Reſ
    0.86
     AttributeSet
    0.85
    expandindo
    0.85
    Act Density 0.000%

    No Known Activations