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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "crash" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ніципалі
    -0.73
    Transcription
    -0.56
     buf
    -0.55
    Palmarès
    -0.55
     autorytatywna
    -0.53
    EndContext
    -0.53
     estekak
    -0.52
    angelo
    -0.52
    Newswire
    -0.52
    
    -0.50
    POSITIVE LOGITS
     crash
    0.97
     Crash
    0.88
    gr
    0.83
    crash
    0.81
     collision
    0.79
     gr
    0.78
    Crash
    0.77
     crashes
    0.76
     shelf
    0.73
     knock
    0.72
    Act Density 0.069%

    No Known Activations