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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical expertise and engineering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stellar
    -0.86
    velt
    -0.79
    hyde
    -0.77
    xual
    -0.69
    lein
    -0.67
    ktop
    -0.67
    olphin
    -0.66
    tsky
    -0.66
     Sheen
    -0.66
    lain
    -0.66
    POSITIVE LOGITS
     specifications
    1.01
     jargon
    0.97
    ity
    0.96
    iencies
    0.95
    ities
    0.93
     feasibility
    0.92
     difficulties
    0.92
     glitches
    0.91
     proficiency
    0.90
     Specifications
    0.89
    Act Density 0.022%

    No Known Activations