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

    Neuronpedia

    INDEX
    Explanations

    references to the act of hearing about something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.76
    isoft
    -0.74
    ila
    -0.74
    igsaw
    -0.73
    eros
    -0.71
    iru
    -0.69
    istration
    -0.69
    arcity
    -0.68
    gradient
    -0.67
    redo
    -0.65
    POSITIVE LOGITS
     voices
    1.25
     Voices
    0.98
     firsthand
    0.96
     footsteps
    0.95
     confessions
    0.94
     aloud
    0.92
     whispers
    0.92
     testimonies
    0.90
     loud
    0.89
     podcasts
    0.89
    Act Density 0.485%

    No Known Activations