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

    Neuronpedia

    INDEX
    Explanations

    words related to operations or the concept of operating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fathers
    -0.18
    e
    -0.17
    olic
    -0.17
    eken
    -0.16
    eper
    -0.16
    eled
    -0.16
    boxed
    -0.16
    볨
    -0.15
    edly
    -0.15
    ey
    -0.15
    POSITIVE LOGITS
    ational
    0.24
    etta
    0.23
    аÑĤив
    0.20
    atings
    0.20
    ATORS
    0.20
    -oper
    0.18
    ativ
    0.18
    ative
    0.18
    ATIONAL
    0.18
    .oper
    0.18
    Act Density 0.007%

    No Known Activations