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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnostic
    -0.14
     åº
    -0.14
    box
    -0.14
     Pert
    -0.14
     Casey
    -0.14
    iable
    -0.13
    ear
    -0.13
    315
    -0.13
    esses
    -0.13
     RESERVED
    -0.13
    POSITIVE LOGITS
    phies
    0.17
     åĤ
    0.16
    LAS
    0.16
    aneous
    0.16
    Forgery
    0.15
    lassian
    0.15
     ******************************************************************************↵
    0.15
    amage
    0.15
    las
    0.14
    adium
    0.14
    Act Density 0.016%

    No Known Activations