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

    Neuronpedia

    INDEX
    Explanations

    terms related to causing damage or negative impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    āra
    -0.51
    CODEC
    -0.50
    '}),
    -0.49
     V
    -0.48
     forms
    -0.46
    /}.
    -0.46
    เงิน
    -0.45
    ILayout
    -0.44
    es
    -0.44
     îna
    -0.42
    POSITIVE LOGITS
     spoiling
    1.41
     spoil
    1.33
     ruining
    1.32
     spoiled
    1.27
     ruined
    1.25
     ruin
    1.25
     spoilt
    1.22
     Ruin
    1.13
     spoils
    1.12
    GEBURTSDATUM
    1.10
    Act Density 0.160%

    No Known Activations