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

    Neuronpedia

    INDEX
    Explanations

    actions associated with performing tasks or making efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.88
     Ise
    -0.84
     Jefus
    -0.79
     ſche
    -0.78
     itſelf
    -0.76
    ChildScrollView
    -0.76
    mybatisplus
    -0.75
     Mers
    -0.73
     ſtate
    -0.73
     themſelves
    -0.72
    POSITIVE LOGITS
     done
    1.64
     do
    1.35
     DONE
    1.29
     Do
    1.28
    done
    1.26
    Do
    1.24
    Doing
    1.24
     DOING
    1.23
     doing
    1.23
    doing
    1.22
    Act Density 0.219%

    No Known Activations