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

    Neuronpedia

    INDEX
    Explanations

    design elements or technical features related to a user interface

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dropdown functionality in design or user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.79
    gregation
    -0.73
    eering
    -0.70
    urally
    -0.68
    apo
    -0.65
    paio
    -0.65
    Wan
    -0.61
    ancial
    -0.60
    aldo
    -0.59
    zza
    -0.59
    POSITIVE LOGITS
    kick
    1.12
    down
    1.08
    downs
    0.98
    outs
    0.84
    backs
    0.83
    plet
    0.81
    bows
    0.79
     hints
    0.77
    lights
    0.77
    drop
    0.77
    Act Density 0.030%

    No Known Activations