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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the verb 'heard'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    heard of or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ferri
    -0.36
    apikey
    -0.33
     Jacobsen
    -0.33
     «
    -0.33
     disegni
    -0.32
    项
    -0.32
     document
    -0.31
    ク
    -0.31
    ผ
    -0.30
     diary
    -0.30
    POSITIVE LOGITS
     heard
    1.35
    Heard
    1.18
     hear
    1.18
    heard
    1.16
     hears
    1.13
     Heard
    1.08
    Hear
    1.07
    hear
    1.05
     Hear
    1.02
     HEAR
    0.97
    Act Density 0.011%

    No Known Activations