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

    Neuronpedia

    INDEX
    Explanations

    safety-related measures and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOPQRST
    -0.55
    esModule
    -0.55
    enfance
    -0.50
     vPvB
    -0.50
    ocity
    -0.48
    เร็
    -0.48
    Moonlight
    -0.48
    šinou
    -0.48
    postValue
    -0.47
     moonlight
    -0.47
    POSITIVE LOGITS
     social
    1.31
    social
    1.15
    Social
    1.15
     SOCIAL
    1.10
     socially
    1.09
     Social
    1.06
    SOCIAL
    1.06
     sociale
    0.97
     социаль
    0.87
    soci
    0.85
    Act Density 0.122%

    No Known Activations