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

    Neuronpedia

    INDEX
    Explanations

    patterns related to achieving goals and outcomes in life

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

    manner and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRI
    -0.64
    HasForeignKey
    -0.56
    enumi
    -0.53
     Parenthood
    -0.51
    PullParser
    -0.50
     tind
    -0.49
    νού
    -0.48
    CDCl
    -0.48
    ItemBackground
    -0.48
    PreferredItem
    -0.43
    POSITIVE LOGITS
     without
    0.70
    fordable
    0.68
    without
    0.67
     reliably
    0.64
     sustainably
    0.62
     reliable
    0.61
    WITHOUT
    0.60
    LookAnd
    0.59
    oredCriteria
    0.57
    ($__
    0.57
    Act Density 0.136%

    No Known Activations