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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "sounds" followed by a descriptive word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing opinions or reactions to statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apsed
    -0.71
    jac
    -0.69
    keyes
    -0.69
    enture
    -0.69
    oled
    -0.67
    udeau
    -0.67
    isner
    -0.67
    aredevil
    -0.67
    odder
    -0.67
    elaide
    -0.66
    POSITIVE LOGITS
     louder
    0.88
     omin
    0.87
    Sounds
    0.84
    tracks
    0.83
     sounding
    0.80
     suspic
    0.77
    lessly
    0.76
     vaguely
    0.76
    bite
    0.75
     deaf
    0.75
    Act Density 0.014%

    No Known Activations