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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "change" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mand
    -0.15
    MAND
    -0.15
    rnd
    -0.15
    ÏĦή
    -0.15
    chet
    -0.15
    anus
    -0.15
    PRS
    -0.14
    æ£ĭ
    -0.14
    éģķãģĦ
    -0.14
    atr
    -0.14
    POSITIVE LOGITS
    hape
    0.17
     tack
    0.17
     diapers
    0.17
     focus
    0.16
    ιÏİ
    0.16
    yntax
    0.16
     direction
    0.16
     Venue
    0.15
     venue
    0.15
     allegiance
    0.15
    Act Density 0.126%

    No Known Activations