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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĭ¥
    -0.16
    èĥŀ
    -0.15
    ena
    -0.15
    pNext
    -0.15
    indir
    -0.15
    IIIK
    -0.15
    ä¼į
    -0.15
    enor
    -0.15
    ziej
    -0.15
    athe
    -0.15
    POSITIVE LOGITS
     Inst
    0.16
    pool
    0.15
     inst
    0.15
    Inst
    0.15
    ober
    0.15
     perfectly
    0.15
    ause
    0.14
    orch
    0.14
    lor
    0.14
    inst
    0.14
    Act Density 0.000%

    No Known Activations