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

    Neuronpedia

    INDEX
    Explanations

    references to ambiguity or uncertainty in various contexts

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

    whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.52
    esModule
    -0.44
     noDo
    -0.40
    zzlies
    -0.39
    vician
    -0.39
    ttle
    -0.38
    GEBURTS
    -0.38
     WebElement
    -0.37
    ceptre
    -0.37
    itv
    -0.37
    POSITIVE LOGITS
     whatever
    0.93
    Whatever
    0.91
     Whatever
    0.91
    whatever
    0.88
     whoever
    0.82
     whichever
    0.81
     whome
    0.73
     Whoever
    0.71
    Whoever
    0.70
     wherever
    0.68
    Act Density 0.158%

    No Known Activations