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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or measurement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional responses or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbollah
    -0.79
     Finally
    -0.78
     Amen
    -0.77
    etheless
    -0.70
    )))
    -0.70
    ''.
    -0.70
    vernment
    -0.69
    ))))
    -0.68
     Lastly
    -0.68
    Finally
    -0.68
    POSITIVE LOGITS
     typically
    0.81
    typically
    0.76
     beginner
    0.73
     commonly
    0.73
     usually
    0.73
     beginners
    0.71
    entimes
    0.67
     traditionally
    0.65
     often
    0.64
    Typically
    0.64
    Act Density 1.547%

    No Known Activations