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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate achievements or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.69
     Dickinson
    -0.68
    orney
    -0.65
     Refresh
    -0.61
    hero
    -0.60
    voy
    -0.60
     Roose
    -0.60
    ingham
    -0.59
     Stephenson
    -0.59
     mayors
    -0.59
    POSITIVE LOGITS
     termed
    0.84
    Downloadha
    0.84
     wrought
    0.80
     accomplished
    0.79
     Learned
    0.75
     happening
    0.72
     indu
    0.71
     perceived
    0.71
    ãĤ´
    0.70
     done
    0.69
    Act Density 0.118%

    No Known Activations