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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "heard," particularly in relation to reports, stories, or rumors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipi
    -0.15
    маз
    -0.14
    ersiz
    -0.14
    illin
    -0.13
    -looking
    -0.13
     photograph
    -0.13
    .jpg
    -0.12
    azzi
    -0.12
    resse
    -0.12
    asl
    -0.12
    POSITIVE LOGITS
     about
    0.36
    /read
    0.35
     stories
    0.28
     whispers
    0.27
     rumors
    0.27
    about
    0.27
     rumours
    0.27
     tales
    0.27
    kening
    0.25
     complaints
    0.24
    Act Density 0.077%

    No Known Activations