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

    Neuronpedia

    INDEX
    Explanations

    phrases related to preparation and prior actions in experiments or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    thanks in advance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prüche
    -0.37
    Prop
    -0.35
     Knudsen
    -0.35
    XtraBars
    -0.32
     Reverso
    -0.32
    TintMode
    -0.32
    hänge
    -0.32
     склад
    -0.31
    BindingResult
    -0.31
    NgModule
    -0.31
    POSITIVE LOGITS
     vooraf
    0.85
     antemano
    0.82
     noDo
    0.81
     pré
    0.81
     prefixed
    0.78
    提前
    0.75
     beforehand
    0.75
     заранее
    0.73
     precede
    0.71
     predetermin
    0.68
    Act Density 0.198%

    No Known Activations