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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiba
    -0.15
    scape
    -0.15
    jamin
    -0.15
    yers
    -0.14
     dl
    -0.14
    hor
    -0.14
    unate
    -0.14
    еÑģÑĤи
    -0.13
    enis
    -0.13
    urb
    -0.13
    POSITIVE LOGITS
     else
    0.17
     kinds
    0.16
     kind
    0.16
     sort
    0.15
    .truth
    0.14
    th
    0.14
    lapping
    0.14
    season
    0.14
    elder
    0.14
    dock
    0.13
    Act Density 0.018%

    No Known Activations