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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ле
    -0.15
    007
    -0.15
    yc
    -0.14
    arf
    -0.14
    iah
    -0.14
    ennes
    -0.14
     Sark
    -0.14
    ertools
    -0.14
    QT
    -0.14
    격
    -0.14
    POSITIVE LOGITS
    ÅĻ
    0.15
     underst
    0.14
     Trib
    0.14
    #__
    0.14
    Playable
    0.14
    ÅĻad
    0.13
     understanding
    0.13
    ÅĻet
    0.13
    Destructor
    0.13
    resco
    0.13
    Act Density 0.053%

    No Known Activations