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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ongoing actions or consistent patterns of behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ियत
    -0.15
    ès
    -0.15
    дÑı
    -0.14
    ihan
    -0.14
    andle
    -0.14
    ìķķ
    -0.14
    andles
    -0.13
    è³¢
    -0.13
     lately
    -0.13
    /key
    -0.13
    POSITIVE LOGITS
    onder
    0.17
    ijo
    0.15
    thro
    0.15
    vb
    0.15
     Glover
    0.14
     novamente
    0.14
    again
    0.14
    à¤Ĥस
    0.14
    hait
    0.14
    ilig
    0.14
    Act Density 0.502%

    No Known Activations