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

    Neuronpedia

    INDEX
    Explanations

    terms related to causes and effects in a systematic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atra
    -0.15
    ongo
    -0.15
    glomer
    -0.15
    ingles
    -0.14
    ------+------+
    -0.14
    clide
    -0.14
    RITE
    -0.14
    ãĢ
    -0.14
    Exclusive
    -0.14
    indows
    -0.14
    POSITIVE LOGITS
     ado
    0.18
    ebin
    0.17
    lings
    0.15
     chic
    0.15
    eil
    0.15
     sure
    0.15
    modo
    0.15
    รà¸ĵ
    0.15
     facilities
    0.15
     facility
    0.15
    Act Density 0.309%

    No Known Activations