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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology startups and their support systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.78
     avenues
    -0.75
     loopholes
    -0.74
     corridors
    -0.74
    bats
    -0.74
    ories
    -0.74
     signatures
    -0.73
    iencies
    -0.73
    ooks
    -0.72
     trophies
    -0.72
    POSITIVE LOGITS
     or
    0.97
    ogram
    0.87
     whose
    0.84
     somewhere
    0.84
    uble
    0.84
     standpoint
    0.83
    ifier
    0.78
     anywhere
    0.78
     lover
    0.78
    alyst
    0.76
    Act Density 2.131%

    No Known Activations