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

    Neuronpedia

    INDEX
    Explanations

    mentions of coaching and coaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ầu
    -0.19
    uously
    -0.17
    utton
    -0.17
    arians
    -0.16
    alist
    -0.15
    anka
    -0.15
    aires
    -0.15
    atik
    -0.15
    oids
    -0.15
    rik
    -0.15
    POSITIVE LOGITS
    (es
    0.24
    istrovstvÃŃ
    0.18
    yard
    0.18
    mans
    0.18
    ella
    0.17
    surf
    0.16
    caffe
    0.15
    elling
    0.15
    essed
    0.15
    inel
    0.15
    Act Density 0.016%

    No Known Activations