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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "heard"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I heard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.80
    igsaw
    -0.79
    ila
    -0.76
    isoft
    -0.71
    apo
    -0.70
    tan
    -0.66
    eros
    -0.65
    anova
    -0.65
    inals
    -0.64
    ggles
    -0.64
    POSITIVE LOGITS
     voices
    1.13
     rumours
    0.98
     rumors
    0.97
     whispers
    0.96
     footsteps
    0.87
     Heard
    0.87
     anecd
    0.87
     confessions
    0.86
     aloud
    0.84
     loud
    0.81
    Act Density 0.033%

    No Known Activations