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

    Neuronpedia

    INDEX
    Explanations

    terms related to unintentional actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardash
    -0.17
     Franklin
    -0.15
    oria
    -0.15
    SPELL
    -0.15
    ington
    -0.14
    adil
    -0.14
    iov
    -0.13
    ëł´
    -0.13
    ibu
    -0.13
    sizes
    -0.13
    POSITIVE LOGITS
    sat
    0.14
    plx
    0.14
    gun
    0.14
    omas
    0.14
    .throw
    0.14
    ationally
    0.14
     omas
    0.14
    ause
    0.14
    aper
    0.13
    exas
    0.13
    Act Density 0.009%

    No Known Activations