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

    Neuronpedia

    INDEX
    Explanations

    social advice and motivational statements

    oai_token-act-pair · gpt-3.5-turbo

    statements about taking action or giving advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     skeletal
    -0.73
    terday
    -0.70
     mutation
    -0.70
     yet
    -0.68
     masked
    -0.64
    awed
    -0.63
     settled
    -0.63
     matched
    -0.63
    uly
    -0.63
     escaping
    -0.62
    POSITIVE LOGITS
     Otherwise
    1.31
     Doing
    1.18
    cknow
    1.18
     Reduce
    1.17
     Become
    1.12
     Then
    1.11
     Provide
    1.11
     Seriously
    1.09
     Ideally
    1.09
     Use
    1.09
    Act Density 0.402%

    No Known Activations