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

    Neuronpedia

    INDEX
    Explanations

    structures related to exceptions and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxt
    -0.16
    ombine
    -0.15
    546
    -0.15
    vester
    -0.14
    rine
    -0.14
    reo
    -0.14
     financier
    -0.13
    ilon
    -0.13
    yper
    -0.13
    OutOfBounds
    -0.13
    POSITIVE LOGITS
    lates
    0.15
    indre
    0.15
    bach
    0.14
    jedn
    0.13
     lorem
    0.13
    .synthetic
    0.13
    IRO
    0.13
    estival
    0.13
     вог
    0.13
    -watch
    0.13
    Act Density 0.011%

    No Known Activations