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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating compatibility or appropriateness

    oai_token-act-pair · gpt-3.5-turbo

    terms that express suitability or appropriateness for specific purposes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aura
    -0.73
    CHA
    -0.71
    berries
    -0.69
    cart
    -0.69
    ires
    -0.68
    dollar
    -0.68
    planes
    -0.67
    iq
    -0.64
     Strait
    -0.64
    stab
    -0.63
    POSITIVE LOGITS
     suitable
    1.01
     candidates
    0.81
     suited
    0.77
     alternatives
    0.76
    lihood
    0.74
     fits
    0.73
     fit
    0.73
     substitutes
    0.72
     fitting
    0.72
     replacements
    0.71
    Act Density 0.015%

    No Known Activations