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

    Neuronpedia

    INDEX
    Explanations

    passive voice constructions and descriptions of processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     opening
    -0.18
     putting
    -0.18
    ibold
    -0.18
     dando
    -0.17
     remaining
    -0.16
     intervening
    -0.16
     bringing
    -0.16
     having
    -0.15
    Ì
    -0.15
    icz
    -0.15
    POSITIVE LOGITS
     divided
    0.25
     preceded
    0.24
     comprised
    0.23
     composed
    0.23
     split
    0.22
     distinguished
    0.21
     subdiv
    0.21
     characterized
    0.20
     based
    0.20
     accompanied
    0.20
    Act Density 0.422%

    No Known Activations