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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or estimation of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lington
    -0.15
    rade
    -0.15
    ombat
    -0.15
    onde
    -0.14
    appName
    -0.14
    ombre
    -0.14
    วย
    -0.14
    retim
    -0.14
     doma
    -0.14
    anches
    -0.13
    POSITIVE LOGITS
     considered
    0.28
     thought
    0.26
     regarded
    0.26
     described
    0.23
     treated
    0.23
     regard
    0.22
     viewed
    0.22
     referred
    0.21
     said
    0.20
    consider
    0.19
    Act Density 0.189%

    No Known Activations