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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs and related phrases indicating intention or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     libertine
    -0.16
    assage
    -0.16
    fon
    -0.15
    807
    -0.15
    ickets
    -0.14
    adena
    -0.14
    avia
    -0.14
    -cigarettes
    -0.13
    reich
    -0.13
    .Xaml
    -0.13
    POSITIVE LOGITS
     soon
    0.27
     Soon
    0.24
    soon
    0.23
    Soon
    0.21
    asts
    0.20
     slash
    0.19
     double
    0.18
     quadr
    0.18
     axe
    0.17
     triple
    0.17
    Act Density 0.118%

    No Known Activations