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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "On" followed by a number, indicating a focus on events or topics organized chronologically or thematically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imli
    -0.14
    demand
    -0.14
    urnished
    -0.14
    оваÑĢи
    -0.14
    acie
    -0.14
    yntax
    -0.13
    /by
    -0.13
    .undefined
    -0.13
    /from
    -0.13
     behalf
    -0.13
    POSITIVE LOGITS
     closer
    0.31
     balance
    0.29
     reflection
    0.28
    es
    0.26
     paper
    0.24
    ward
    0.22
    balance
    0.22
    reflection
    0.22
     inspection
    0.22
     further
    0.22
    Act Density 0.064%

    No Known Activations