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

    Neuronpedia

    INDEX
    Explanations

    references to automobile accidents and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errupted
    -0.15
    нки
    -0.15
    dbg
    -0.15
     Shooter
    -0.14
    chedulers
    -0.14
     murderers
    -0.14
    êu
    -0.14
     Killing
    -0.13
     má
    -0.13
    ãĥ¯ãĤ¤ãĥĪ
    -0.13
    POSITIVE LOGITS
     accident
    0.54
    acc
    0.49
     accidents
    0.47
     Accident
    0.42
    Acc
    0.41
    _acc
    0.40
     Acc
    0.40
     crash
    0.39
     acc
    0.37
     collision
    0.36
    Act Density 0.083%

    No Known Activations