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

    Neuronpedia

    INDEX
    Explanations

    words related to radioactivity and nuclear elements

    oai_token-act-pair · gpt-3.5-turbo

    plural and past tense forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NOW
    -0.64
     Doodle
    -0.63
     Yard
    -0.63
     Destroyer
    -0.63
     Blues
    -0.62
     Darling
    -0.61
    glers
    -0.61
    iage
    -0.61
    Ĥª
    -0.61
     Victory
    -0.60
    POSITIVE LOGITS
    etr
    0.92
    ith
    0.83
    idential
    0.83
    emic
    0.81
    ilon
    0.80
    itary
    0.79
    hiba
    0.79
    peria
    0.79
    estial
    0.79
    ophile
    0.78
    Act Density 0.125%

    No Known Activations