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

    Neuronpedia

    INDEX
    Explanations

    contractions and certain auxiliary verbs that indicate uncertainty or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.15
    orca
    -0.15
    ickle
    -0.14
    лада
    -0.14
    illac
    -0.14
    âĶģâĶ
    -0.14
    celik
    -0.14
    arden
    -0.14
    Zip
    -0.14
    åģ
    -0.14
    POSITIVE LOGITS
    kees
    0.16
    uns
    0.15
    лами
    0.15
    ICA
    0.15
    kest
    0.14
    iasi
    0.14
     Sandy
    0.14
    kit
    0.14
    -pocket
    0.14
    icos
    0.14
    Act Density 0.008%

    No Known Activations