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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing possibility and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovu
    -0.18
    ivos
    -0.15
    bers
    -0.15
    ulaire
    -0.14
    resizing
    -0.14
    entin
    -0.14
    _DLL
    -0.14
    ën
    -0.14
    ercul
    -0.14
    ulk
    -0.13
    POSITIVE LOGITS
     they
    0.29
     we
    0.29
     it
    0.26
     he
    0.19
     you
    0.19
     she
    0.19
    /do
    0.19
     они
    0.17
     this
    0.17
    they
    0.17
    Act Density 0.073%

    No Known Activations