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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases of denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strup
    -0.16
    leton
    -0.15
    BuilderFactory
    -0.14
    à¹ĥห
    -0.14
    zhou
    -0.14
    áºŃt
    -0.14
    _chg
    -0.14
    imar
    -0.13
    Ware
    -0.13
     rowspan
    -0.13
    POSITIVE LOGITS
    شر
    0.19
    iface
    0.16
    ETS
    0.16
    just
    0.15
    Äħż
    0.15
     just
    0.15
    ensch
    0.14
    CHK
    0.14
    ets
    0.14
     Tort
    0.14
    Act Density 0.036%

    No Known Activations