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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate knowledge or expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.54
    IntoConstraints
    -0.51
    bledon
    -0.51
    qui
    -0.48
    PerformLayout
    -0.48
    assi
    -0.47
    hable
    -0.47
    ascii
    -0.46
    pic
    -0.46
    éric
    -0.45
    POSITIVE LOGITS
     كومونز
    0.79
    OrBuilder
    0.66
    seamnă
    0.65
     ſtate
    0.63
     Jefus
    0.63
     suaminya
    0.62
     intricacies
    0.60
     myſelf
    0.57
     houſe
    0.56
    oa̍t
    0.55
    Act Density 0.456%

    No Known Activations