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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñana
    -0.07
    ertz
    -0.07
    ffi
    -0.07
    ashi
    -0.06
    auc
    -0.06
    zim
    -0.06
    ocket
    -0.06
    edor
    -0.06
    adol
    -0.06
    ritz
    -0.06
    POSITIVE LOGITS
     porr
    0.07
    erve
    0.07
     Pod
    0.06
    ERVE
    0.06
    statt
    0.06
     POD
    0.06
    phants
    0.06
     respective
    0.06
    vertiser
    0.06
     pod
    0.06
    Act Density 0.057%

    No Known Activations