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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "attachment" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -0.49
     fut
    -0.46
    resist
    -0.46
    JsonHelper
    -0.43
    CER
    -0.43
    Cast
    -0.42
    Bend
    -0.41
     stol
    -0.41
    bend
    -0.41
    ques
    -0.41
    POSITIVE LOGITS
    Attachment
    0.81
     attachment
    0.77
     ATTACH
    0.76
     Attachments
    0.74
     Attachment
    0.73
     attachments
    0.72
     attaching
    0.70
     attached
    0.68
    Attachments
    0.67
    Attached
    0.66
    Act Density 0.185%

    No Known Activations