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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "exception" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ι
    -0.17
    _exceptions
    -0.16
    entic
    -0.16
    ExecutionContext
    -0.15
    gie
    -0.15
    cano
    -0.14
    ume
    -0.14
    ernet
    -0.14
    gende
    -0.14
    hest
    -0.14
    POSITIVE LOGITS
    nal
    0.27
    ality
    0.26
    ally
    0.25
    ively
    0.21
    ALLY
    0.21
    nelle
    0.20
    /error
    0.20
    aldi
    0.18
    ities
    0.18
    alist
    0.18
    Act Density 0.026%

    No Known Activations