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

    Neuronpedia

    INDEX
    Explanations

    negative attributes related to communication and social interaction

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

    lack of friendliness or warmth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
    FormTagHelper
    -0.69
    Personensuche
    -0.66
    Rüyada
    -0.66
    +#+#
    -0.61
    elemField
    -0.61
    ErrUnexpectedEOF
    -0.60
    GOTREF
    -0.60
     transfieras
    -0.58
    principalColumn
    -0.58
    POSITIVE LOGITS
     cold
    0.47
     coldness
    0.42
     fría
    0.42
     coldly
    0.40
    冷漠
    0.39
     unfriendly
    0.38
    Cold
    0.36
    cold
    0.35
     soğ
    0.35
     stiff
    0.34
    Act Density 0.054%

    No Known Activations