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

    Neuronpedia

    INDEX
    Explanations

    expressions related to apologies and justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dodd
    -0.15
     Decom
    -0.15
    rg
    -0.14
    æĿī
    -0.14
    arest
    -0.14
    argument
    -0.14
     Active
    -0.14
    744
    -0.14
    led
    -0.14
     Ant
    -0.13
    POSITIVE LOGITS
    yme
    0.18
    yne
    0.17
    uele
    0.17
    iona
    0.16
     iParam
    0.16
    INET
    0.16
    vale
    0.15
    opoulos
    0.15
     Gazette
    0.15
    ìħĶ
    0.15
    Act Density 0.171%

    No Known Activations