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

    Neuronpedia

    INDEX
    Explanations

    references to usefulness and support in the content

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

    Sentences expressing something is useful or helpful

    np_acts-logits-general · gemini-2.0-flash

    useful and helpful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.69
    Hentet
    -0.66
    JspWriter
    -0.64
     שוליים
    -0.63
    expandindo
    -0.60
    tagHelperRunner
    -0.60
    +#+#
    -0.59
     VIDEOTAPE
    -0.58
    limus
    -0.57
     älskar
    -0.57
    POSITIVE LOGITS
     useful
    2.37
     Useful
    2.04
    useful
    2.04
     helpful
    2.00
    Useful
    1.89
     usefulness
    1.81
     utile
    1.68
    helpful
    1.66
     útil
    1.61
     Helpful
    1.53
    Act Density 0.381%

    No Known Activations