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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exceptions and exceptional circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _exceptions
    -0.18
    _exception
    -0.16
    _except
    -0.16
    entic
    -0.15
    gie
    -0.15
    ichel
    -0.14
    cano
    -0.14
    aska
    -0.14
    ernet
    -0.14
    ι
    -0.14
    POSITIVE LOGITS
    nal
    0.30
    ality
    0.25
    ally
    0.25
    ively
    0.22
    nelle
    0.21
    ALLY
    0.21
    ities
    0.19
     circumstances
    0.18
    alist
    0.18
    ordinary
    0.18
    Act Density 0.028%

    No Known Activations