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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and acknowledgment

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

    point out that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.91
    󠁣
    -0.79
    PYX
    -0.75
    MigrationBuilder
    -0.73
     nakalista
    -0.73
     kasarigan
    -0.73
     ſind
    -0.68
    ihnach
    -0.68
     ſei
    -0.68
     Numerade
    -0.67
    POSITIVE LOGITS
     myself
    0.43
    AlterField
    0.40
     that
    0.37
     here
    0.35
     recently
    0.35
     something
    0.31
     my
    0.31
     today
    0.31
     recent
    0.29
     also
    0.28
    Act Density 0.017%

    No Known Activations