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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or steps in a procedure

    oai_token-act-pair · gpt-3.5-turbo

    attributions of importance or significance to statements or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.78
    cookie
    -0.65
    chev
    -0.65
    abal
    -0.64
    avin
    -0.62
    waukee
    -0.61
    elve
    -0.61
    tight
    -0.60
    opez
    -0.59
    flake
    -0.58
    POSITIVE LOGITS
     done
    1.02
     accomplished
    1.01
     achieved
    0.98
     contrasted
    0.98
     followed
    0.92
     because
    0.89
     supplemented
    0.89
     why
    0.87
     accompanied
    0.87
     untrue
    0.86
    Act Density 0.134%

    No Known Activations