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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" and its use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apiro
    -0.17
     sẵn
    -0.15
    andon
    -0.15
    agem
    -0.14
    _SINGLE
    -0.14
    ansk
    -0.13
    esto
    -0.13
     heck
    -0.13
    xis
    -0.13
    ready
    -0.13
    POSITIVE LOGITS
     dealing
    0.27
     faced
    0.23
     there
    0.22
     dealt
    0.21
     done
    0.19
     considering
    0.19
     compared
    0.18
     applied
    0.17
     facing
    0.17
     Done
    0.17
    Act Density 0.078%

    No Known Activations