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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or questioning

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

    Follows first-person pronouns or pertains to feelings

    np_acts-logits-general · gemini-2.0-flash

    tone and nuance detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.57
     kasarigan
    -0.57
     ModelExpression
    -0.50
    AnchorStyles
    -0.50
     CreateTagHelper
    -0.50
    IsMutable
    -0.48
    pulumi
    -0.47
    PhysRevD
    -0.47
    +#+#
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
     sounding
    0.42
     sarcasm
    0.38
     paragraph
    0.37
     speak
    0.36
     shrugs
    0.34
     tone
    0.33
     sounds
    0.33
     italic
    0.33
    这话
    0.33
     mood
    0.32
    Act Density 0.319%

    No Known Activations