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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olle
    -0.15
    yne
    -0.15
    hon
    -0.15
    athed
    -0.14
    &
    -0.14
    dings
    -0.14
    zcze
    -0.14
    T
    -0.14
     paramet
    -0.13
     Del
    -0.13
    POSITIVE LOGITS
    0
    0.31
    5
    0.23
    7
    0.20
    75
    0.19
    8
    0.19
    9
    0.18
    6
    0.18
    3
    0.18
    4
    0.17
    2
    0.17
    Act Density 0.030%

    No Known Activations