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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors of experiences or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zer
    -0.16
    strup
    -0.16
    ikk
    -0.15
    Ñİк
    -0.15
    ust
    -0.15
    ábado
    -0.15
    oo
    -0.14
     pl
    -0.14
    CHED
    -0.14
    ched
    -0.14
    POSITIVE LOGITS
    ieder
    0.19
    ntax
    0.18
    resco
    0.17
    GMEM
    0.16
    ablish
    0.15
    orce
    0.15
    è³
    0.15
    889
    0.15
    ecer
    0.15
    phans
    0.14
    Act Density 0.045%

    No Known Activations