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

    Neuronpedia

    INDEX
    Explanations

    references to symposiums or conferences

    oai_token-act-pair · gpt-3.5-turbo

    references to symposiums or conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    patrick
    -0.77
    WARD
    -0.73
    ships
    -0.69
    holding
    -0.68
    erness
    -0.67
     conversion
    -0.67
    pour
    -0.67
     wagon
    -0.66
     Morty
    -0.65
    LESS
    -0.64
    POSITIVE LOGITS
    posium
    1.51
    phony
    1.12
    ptoms
    1.09
     Sym
    0.97
    pt
    0.87
    onic
    0.86
    ph
    0.86
    pton
    0.84
    Sym
    0.82
    unia
    0.81
    Act Density 0.018%

    No Known Activations