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

    Neuronpedia

    INDEX
    Explanations

    references to prototypes

    oai_token-act-pair · gpt-3.5-turbo

    references to prototypes or experimental designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.86
    andra
    -0.84
    die
    -0.79
    arching
    -0.78
    vation
    -0.75
    wind
    -0.75
    bourne
    -0.74
    dos
    -0.72
    aiman
    -0.71
    leans
    -0.69
    POSITIVE LOGITS
     prototype
    1.07
     prototypes
    1.02
    prototype
    0.85
     Prototype
    0.84
     sketches
    0.82
    smanship
    0.81
    hesis
    0.77
     template
    0.73
     sketch
    0.71
     prototyp
    0.71
    Act Density 0.025%

    No Known Activations