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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate direction or change over time

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

    "From" followed by a variety of words

    np_acts-logits-general · gemini-2.0-flash

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     navíc
    -0.53
    mayın
    -0.50
     zugleich
    -0.49
     wikipagina
    -0.49
     giudizio
    -0.49
     preocupes
    -0.47
    참고
    -0.47
     frattempo
    -0.47
     berikutnya
    -0.45
     myö
    -0.45
    POSITIVE LOGITS
    '][]
    0.82
    enumi
    0.82
     nahilalakip
    0.81
    */,
    0.77
    ")]
    0.75
    AddTagHelper
    0.75
    клопе
    0.71
    :+:
    0.71
     लेकर
    0.71
    ']);
    0.71
    Act Density 0.133%

    No Known Activations