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

    Neuronpedia

    INDEX
    Explanations

    references to fundamental concepts or foundational knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.84
    rone
    -0.72
    deen
    -0.67
    arma
    -0.64
    rama
    -0.63
    lex
    -0.62
    emale
    -0.62
    rio
    -0.61
    ammers
    -0.60
    ove
    -0.60
    POSITIVE LOGITS
     thereof
    0.95
    hooting
    0.82
    layer
    0.81
     abound
    0.78
     of
    0.77
     pertaining
    0.75
    ensical
    0.70
    etting
    0.70
     basics
    0.70
    heet
    0.70
    Act Density 0.023%

    No Known Activations