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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and specialized terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.16
    yn
    -0.16
    amiento
    -0.16
    eh
    -0.16
    etas
    -0.15
    ificio
    -0.15
    yon
    -0.15
    stra
    -0.15
    enschaft
    -0.15
    chants
    -0.15
    POSITIVE LOGITS
    tered
    0.28
    ismatic
    0.28
    coal
    0.28
    itable
    0.24
    itably
    0.24
    isma
    0.24
    akter
    0.23
    izard
    0.21
    leston
    0.21
    κÏĦη
    0.20
    Act Density 0.015%

    No Known Activations