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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply hearsay or subjective descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a perception or impression of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enture
    -0.67
    odder
    -0.66
     ILCS
    -0.65
     Lann
    -0.65
     Blackhawks
    -0.64
    apsed
    -0.64
    isin
    -0.64
    Avg
    -0.63
     Ys
    -0.62
    keyes
    -0.62
    POSITIVE LOGITS
    Sounds
    1.12
     sounds
    1.08
     Sounds
    1.06
     sounded
    1.03
     noises
    0.96
     sound
    0.93
     sounding
    0.88
    sound
    0.86
     louder
    0.84
     omin
    0.83
    Act Density 0.009%

    No Known Activations