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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the consequences of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ause
    -0.15
    aes
    -0.14
    hammer
    -0.14
    coles
    -0.14
     wur
    -0.14
    kontakte
    -0.14
    anni
    -0.14
    uchs
    -0.14
    enos
    -0.14
    éĴ®
    -0.13
    POSITIVE LOGITS
    .Parameters
    0.16
    elt
    0.16
     rad
    0.15
    oma
    0.14
    czy
    0.14
    ertificate
    0.13
    inite
    0.13
    )const
    0.13
    ãģ¹
    0.13
    ierten
    0.12
    Act Density 0.145%

    No Known Activations