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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases signifying potentiality or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iless
    -0.15
    auer
    -0.15
    _weather
    -0.15
    undle
    -0.14
    iod
    -0.14
     باز
    -0.14
    ailer
    -0.14
    .nih
    -0.13
    monic
    -0.13
    Ø´ÙĪر
    -0.13
    POSITIVE LOGITS
    aticon
    0.16
    oog
    0.16
    oje
    0.16
    endl
    0.15
     Poz
    0.15
     Hammond
    0.15
    horn
    0.15
    orns
    0.15
    apsed
    0.15
    elon
    0.15
    Act Density 0.001%

    No Known Activations