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

    Neuronpedia

    INDEX
    Explanations

    terms related to exceptions and exceptional circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _exceptions
    -0.18
    _exception
    -0.17
    gie
    -0.16
    _except
    -0.16
    ichel
    -0.15
    entic
    -0.15
    cano
    -0.14
    asonic
    -0.14
    Exceptions
    -0.14
     exceptions
    -0.14
    POSITIVE LOGITS
    nal
    0.28
    ality
    0.27
    ally
    0.24
    ively
    0.23
    nelle
    0.22
    /error
    0.21
    ALLY
    0.20
    aldi
    0.18
    ities
    0.17
    alist
    0.17
    Act Density 0.025%

    No Known Activations