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

    Neuronpedia

    INDEX
    Explanations

    terms related to aptitude and ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.19
    h
    -0.17
    istica
    -0.16
    EMENT
    -0.16
    r
    -0.15
     Rica
    -0.15
     Oliver
    -0.15
     ringing
    -0.15
    riers
    -0.14
    kie
    -0.14
    POSITIVE LOGITS
    itude
    0.38
    itudes
    0.30
    ITUDE
    0.29
    itud
    0.23
    ech
    0.20
    613
    0.20
    eka
    0.19
    imizer
    0.18
    ivate
    0.17
    ember
    0.17
    Act Density 0.022%

    No Known Activations