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

    Neuronpedia

    INDEX
    Explanations

    questions and sentiments related to communication and relationships

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

    Informal online chat/forum communication

    np_acts-logits-general · gemini-2.0-flash

    informal statements and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Certainly
    -0.68
    Whilst
    -0.66
     Considerable
    -0.61
    Given
    -0.61
    IsMutable
    -0.61
    )";
    -0.60
    horabuena
    -0.60
     Certainly
    -0.60
    خرى
    -0.59
    ]!='
    -0.59
    POSITIVE LOGITS
     im
    1.05
     i
    0.83
     ill
    0.83
     Im
    0.73
    nvm
    0.70
     its
    0.70
     hes
    0.70
     ive
    0.69
    Im
    0.69
     idk
    0.68
    Act Density 0.259%

    No Known Activations