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

    Neuronpedia

    INDEX
    Explanations

    references to horses and related terms in various contexts

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

    associated with horses

    np_acts-logits-general · gemini-2.0-flash

    horse and equine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.63
    Hentet
    -0.60
    MigrationBuilder
    -0.60
    PreInfinity
    -0.60
     AssemblyCulture
    -0.59
    EDEFAULT
    -0.58
     Eilish
    -0.58
     ostavi
    -0.56
    __*/
    -0.54
     betweenstory
    -0.54
    POSITIVE LOGITS
     horse
    1.89
     horses
    1.84
     Horse
    1.74
    horse
    1.69
    Horse
    1.68
     Horses
    1.64
     HORSE
    1.59
    Horses
    1.50
     caballos
    1.49
    horses
    1.49
    Act Density 0.298%

    No Known Activations