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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and pronouns, particularly in phrases that indicate action or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .IContainer
    -0.16
     fragment
    -0.15
    fragment
    -0.15
    msp
    -0.14
    gL
    -0.14
    _DEPEND
    -0.14
     fragmentation
    -0.14
    InputChange
    -0.14
    zzo
    -0.14
    éĻ¢
    -0.14
    POSITIVE LOGITS
    orris
    0.20
    chl
    0.17
    atomy
    0.16
    elles
    0.15
    erland
    0.15
    PS
    0.15
    ence
    0.15
     Burl
    0.15
    ly
    0.14
    otto
    0.14
    Act Density 0.030%

    No Known Activations