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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "done" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovací
    -0.71
    nasel
    -0.67
     carburant
    -0.67
     GenerationType
    -0.64
    ylvan
    -0.63
     suivants
    -0.63
    Према
    -0.63
     humain
    -0.60
     carriera
    -0.59
     pleins
    -0.59
    POSITIVE LOGITS
    done
    1.36
    Done
    1.29
    DONE
    1.06
     Done
    0.92
     tragedy
    0.71
    Гото
    0.59
    Pyx
    0.59
     DONE
    0.57
    Pron
    0.56
    tra
    0.56
    Act Density 0.130%

    No Known Activations