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

    Neuronpedia

    INDEX
    Explanations

    words related to physical activities and actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.79
     AssemblyCompany
    -0.79
    ſelves
    -0.77
    "):
    -0.74
     Efq
    -0.72
    ')['
    -0.71
     Majefty
    -0.69
    "",
    -0.69
    prefixer
    -0.67
    ſelf
    -0.66
    POSITIVE LOGITS
     مشين
    0.54
    es
    0.53
    ord
    0.48
    bcryptjs
    0.47
    teman
    0.46
    uffff
    0.46
     Lightboxes
    0.46
    hpur
    0.45
    arg
    0.45
    انی
    0.44
    Act Density 0.048%

    No Known Activations