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

    Neuronpedia

    INDEX
    Explanations

    terms related to suitability and appropriateness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.82
     Firestone
    -0.67
     Hump
    -0.64
    rboles
    -0.60
    mo
    -0.60
    квар
    -0.58
    硫
    -0.58
    нець
    -0.58
    k
    -0.58
     Eber
    -0.57
    POSITIVE LOGITS
    uitable
    1.20
    nappropriate
    1.14
    suitable
    1.08
     suitable
    1.08
     suited
    1.06
    suited
    1.06
     Suit
    1.04
     Suitable
    1.03
     suitability
    0.99
     referenties
    0.98
    Act Density 0.093%

    No Known Activations