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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical rates or occurrences of various events

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical rates associated with negative outcomes or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     severed
    -0.71
    ADRA
    -0.68
    ICLE
    -0.64
     Gleaming
    -0.64
    Pub
    -0.63
    tiny
    -0.63
     disapp
    -0.62
    ISTORY
    -0.62
     SECTION
    -0.61
    ¾
    -0.60
    POSITIVE LOGITS
     (>
    0.99
    ovi
    0.89
     (<
    0.76
     variability
    0.71
     levels
    0.69
     rates
    0.67
    aroo
    0.66
     throughput
    0.66
     dur
    0.66
    than
    0.65
    Act Density 0.211%

    No Known Activations