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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions or comments about events or objects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     sealing
    -0.73
     streng
    -0.71
     dispers
    -0.71
     ingred
    -0.69
    rift
    -0.65
     confir
    -0.65
    eta
    -0.63
    sufficient
    -0.63
     arrang
    -0.63
     Secondly
    -0.62
    POSITIVE LOGITS
     cringe
    0.91
     cliché
    0.91
     pundits
    0.88
     wondering
    0.83
     understandably
    0.83
     clich
    0.81
     familiar
    0.81
     rightly
    0.78
     tempting
    0.77
     headlines
    0.76
    Act Density 3.478%

    No Known Activations