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

    Neuronpedia

    INDEX
    Explanations

    words related to increasing trends or frequencies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.77
     للمعارف
    -0.68
    AndEndTag
    -0.67
     ALLE
    -0.65
     ddelweddau
    -0.63
     تانيه
    -0.63
     Bote
    -0.62
     WaitForSeconds
    -0.60
     Schofield
    -0.60
     UIImage
    -0.59
    POSITIVE LOGITS
    ctuation
    0.65
     Henning
    0.61
     turns
    0.60
     vira
    0.60
    kháu
    0.59
    makeConstraints
    0.59
    ="/">
    0.57
     Turning
    0.57
    Turning
    0.56
    hythm
    0.56
    Act Density 0.009%

    No Known Activations