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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "up" and its various forms in contexts related to growth or elevation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     barring
    -0.70
     electing
    -0.68
     demonstrating
    -0.68
     guaranteeing
    -0.68
     authorizing
    -0.67
     sending
    -0.66
     rejecting
    -0.66
     theirs
    -0.66
    ère
    -0.65
     extending
    -0.65
    POSITIVE LOGITS
     oneself
    0.80
     Yourself
    0.78
    });
    0.68
    itness
    0.68
    iped
    0.67
    olitical
    0.66
    ictionary
    0.66
    ricular
    0.66
    aughs
    0.66
     Cause
    0.64
    Act Density 0.557%

    No Known Activations