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

    Neuronpedia

    INDEX
    Explanations

    references to past actions or states in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bject
    -0.16
    .Ui
    -0.16
    iland
    -0.16
    OptionPane
    -0.16
    stroy
    -0.15
    stoff
    -0.15
    aji
    -0.15
    boom
    -0.14
     parch
    -0.14
    ê
    -0.14
    POSITIVE LOGITS
     able
    0.23
     ability
    0.17
     Ability
    0.16
    avl
    0.15
     Able
    0.14
     willing
    0.14
     refl
    0.14
     ÙĤادر
    0.14
     silent
    0.14
     sing
    0.13
    Act Density 0.409%

    No Known Activations