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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases indicating various types of sounds or emissions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sounded" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hibition
    -0.76
    venge
    -0.74
    arov
    -0.70
    eve
    -0.67
     Janeiro
    -0.67
     Geh
    -0.65
    orate
    -0.65
    ister
    -0.63
    jar
    -0.63
    vert
    -0.62
    POSITIVE LOGITS
     sounded
    1.21
     sounding
    1.00
     omin
    0.92
     louder
    0.89
     sound
    0.88
     sounds
    0.87
     noises
    0.87
     nodd
    0.85
     alarms
    0.84
     tremend
    0.83
    Act Density 0.004%

    No Known Activations