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

    Neuronpedia

    INDEX
    Explanations

    adjectives or phrases describing something as perfect, ideal, appropriate, or a good fit

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing something as ideal or perfect for a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leness
    -0.84
    ngth
    -0.84
    phies
    -0.76
    raint
    -0.72
    rir
    -0.69
    common
    -0.69
    thood
    -0.69
    ravings
    -0.68
    anners
    -0.68
    RAW
    -0.66
    POSITIVE LOGITS
     candidate
    1.25
     target
    1.17
     choice
    1.17
     fit
    1.16
     place
    1.14
     opportunity
    1.12
     venue
    1.11
     destination
    1.08
     avenue
    1.03
     pairing
    1.00
    Act Density 0.160%

    No Known Activations