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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs indicating states of being or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terior
    -0.16
     Whilst
    -0.15
    gregate
    -0.15
    prior
    -0.14
    ãģ«ãģ¦
    -0.14
     CONSEQUENTIAL
    -0.14
    exas
    -0.14
    Prior
    -0.13
    à¥įà¤Ĺत
    -0.13
     WHATSOEVER
    -0.13
    POSITIVE LOGITS
     Mister
    0.15
     permit
    0.15
     --
    0.15
     Reuters
    0.15
     clos
    0.14
    azy
    0.14
    .
    0.14
    Reuters
    0.14
     okay
    0.14
     permitting
    0.14
    Act Density 0.001%

    No Known Activations