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

    Neuronpedia

    INDEX
    Explanations

    words related to operations or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.18
     Fathers
    -0.18
    볨
    -0.17
    enger
    -0.16
    rig
    -0.15
    eled
    -0.15
    variants
    -0.15
    r
    -0.15
    ey
    -0.14
    ek
    -0.14
    POSITIVE LOGITS
    ational
    0.27
    etta
    0.25
    -oper
    0.23
    ATIONAL
    0.22
     operated
    0.21
    atings
    0.21
    ativ
    0.21
    .oper
    0.21
    ating
    0.21
     oper
    0.20
    Act Density 0.006%

    No Known Activations