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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ect
    -0.20
    osta
    -0.15
    line
    -0.15
    nt
    -0.15
    list
    -0.14
     quand
    -0.14
    celik
    -0.14
    ëĭĺ
    -0.14
    olle
    -0.14
    andon
    -0.14
    POSITIVE LOGITS
    yeah
    0.20
    sure
    0.19
    redient
    0.17
    hhh
    0.17
     sure
    0.17
    tember
    0.16
    emek
    0.16
    sian
    0.16
    .GridView
    0.16
    Yeah
    0.16
    Act Density 0.018%

    No Known Activations