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

    Neuronpedia

    INDEX
    Explanations

    terms related to consequences, especially in the context of health and environmental impacts

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

    Prepositions followed by nouns

    np_acts-logits-general · gemini-2.0-flash

    discussion or comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.81
    #+#
    -0.79
     Signalez
    -0.76
    Personensuche
    -0.70
     nahilalakip
    -0.62
    msgTypes
    -0.60
    ">//
    -0.59
    EDEFAULT
    -0.58
    thâu
    -0.58
    Халык
    -0.58
    POSITIVE LOGITS
     comment
    0.95
     comments
    0.78
     thought
    0.77
     discussion
    0.68
     comentario
    0.67
     summary
    0.67
     coment
    0.67
     comentário
    0.66
    comment
    0.66
    Comment
    0.66
    Act Density 1.204%

    No Known Activations