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

    Neuronpedia

    INDEX
    Explanations

    contractions of the word "it is" and similar phrases indicating existence or action

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

    but conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esModule
    -0.53
    UnusedPrivate
    -0.50
    interopRequire
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    MarshalTo
    -0.46
    Referencer
    -0.44
     împre
    -0.44
    WireFormatLite
    -0.44
     pomen
    -0.44
    RenderAtEndOf
    -0.42
    POSITIVE LOGITS
     but
    1.02
     But
    0.92
    But
    0.88
    but
    0.83
     BUT
    0.82
    但
    0.79
     pero
    0.71
     nhưng
    0.71
    但他
    0.70
     tetapi
    0.69
    Act Density 0.220%

    No Known Activations