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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and related terms that indicate presence or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rr
    -0.17
    ByExample
    -0.15
    807
    -0.15
    toy
    -0.14
    .library
    -0.14
    tol
    -0.14
    izr
    -0.14
    idity
    -0.14
    ergency
    -0.14
     pres
    -0.13
    POSITIVE LOGITS
     Zust
    0.15
    heck
    0.15
    Ñģли
    0.14
    emer
    0.14
    tems
    0.13
     ë³ij
    0.13
     Moz
    0.13
    dns
    0.13
    artz
    0.13
     Chairs
    0.13
    Act Density 0.044%

    No Known Activations