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

    Neuronpedia

    INDEX
    Explanations

    clauses related to rules, obligations, and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ins
    -0.15
    ãĥ«ãĥī
    -0.15
    mins
    -0.14
    TION
    -0.14
    ạ
    -0.13
     Maiden
    -0.13
     воÑĢ
    -0.13
    isure
    -0.13
    INCLUDED
    -0.13
    ipple
    -0.13
    POSITIVE LOGITS
    оваÑĢ
    0.17
    riors
    0.17
    NullOr
    0.15
    mart
    0.14
    Unless
    0.14
    aches
    0.14
    Dat
    0.14
     Dat
    0.14
    Carthy
    0.13
    adlo
    0.13
    Act Density 0.108%

    No Known Activations