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

    Neuronpedia

    INDEX
    Explanations

    attributes of personality, particularly those that are positive or whimsical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    simum
    -0.59
    ⓘ
    -0.56
     geometry
    -0.55
    jän
    -0.53
     */,
    -0.53
    ArrowToggle
    -0.53
     geometrical
    -0.52
     geometries
    -0.52
    Geometry
    -0.51
    miert
    -0.50
    POSITIVE LOGITS
     personality
    0.84
    personality
    0.83
    Personality
    0.77
     Personality
    0.73
     personalidade
    0.68
     CascadeType
    0.66
    MethodManager
    0.65
     personalidad
    0.64
     demeanor
    0.64
     personalities
    0.64
    Act Density 0.354%

    No Known Activations