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

    Neuronpedia

    INDEX
    Explanations

    expressions of comparison and degree in descriptions

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

    intensifiers followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.40
     BrowserModule
    -0.36
    ualaikum
    -0.35
     fernández
    -0.34
     málaga
    -0.34
     HasFactory
    -0.34
    simum
    -0.33
     houſe
    -0.33
    cagon
    -0.33
     sánchez
    -0.33
    POSITIVE LOGITS
    extAlignment
    0.63
    OGND
    0.57
     quirky
    0.56
     surreal
    0.55
    addContainerGap
    0.55
     savory
    0.55
     purely
    0.54
    󠁣
    0.54
     pure
    0.53
     nons
    0.52
    Act Density 0.094%

    No Known Activations