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

    Neuronpedia

    INDEX
    Explanations

    references to abnormal or symptoms-related medical conditions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Waray
    -0.67
    tov
    -0.60
    elev
    -0.58
     Administrativna
    -0.56
     stöd
    -0.55
     Kombat
    -0.54
    ถม
    -0.54
    henge
    -0.54
    帖最后由
    -0.52
    boy
    -0.52
    POSITIVE LOGITS
     tertiary
    1.93
     Tertiary
    1.63
    Tertiary
    1.33
    tiary
    0.94
     terci
    0.82
    acies
    0.81
     imparted
    0.72
     ***!
    0.71
     impart
    0.71
     imparting
    0.65
    Act Density 0.001%

    No Known Activations