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

    Neuronpedia

    INDEX
    Explanations

    words indicating specific locations or measures of value and time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecera
    -0.16
    onas
    -0.16
    idon
    -0.16
    ebo
    -0.15
    iral
    -0.15
    heck
    -0.15
    ideon
    -0.15
    eid
    -0.14
    umbn
    -0.14
    zas
    -0.14
    POSITIVE LOGITS
    pit
    0.18
     Saul
    0.15
    ares
    0.15
    uis
    0.14
     Blackburn
    0.14
     TMPro
    0.14
    urb
    0.13
     inj
    0.13
     Fah
    0.13
     Sakura
    0.13
    Act Density 0.008%

    No Known Activations