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

    Neuronpedia

    INDEX
    Explanations

    phrases that relate to exceptions and unique cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entic
    -0.17
    dden
    -0.15
    illac
    -0.15
    mae
    -0.15
    pone
    -0.15
    iggers
    -0.15
    manship
    -0.14
    cano
    -0.14
    aterno
    -0.14
    igkeit
    -0.14
    POSITIVE LOGITS
    ality
    0.28
    ally
    0.28
    nal
    0.26
    ively
    0.23
    nelle
    0.22
     circumstances
    0.21
    al
    0.20
    ities
    0.20
    ALLY
    0.20
    _handling
    0.20
    Act Density 0.025%

    No Known Activations