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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "return" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĻµ
    -0.18
    iras
    -0.17
    ledon
    -0.17
    out
    -0.16
     turn
    -0.16
    uet
    -0.14
    ænd
    -0.14
    ÑħÑĥ
    -0.14
    elier
    -0.14
    dar
    -0.14
    POSITIVE LOGITS
    ees
    0.31
    KeyType
    0.22
     home
    0.20
     whence
    0.20
    _sequences
    0.19
    ee
    0.18
    alker
    0.18
    ToBounds
    0.17
    749
    0.17
    edException
    0.16
    Act Density 0.031%

    No Known Activations