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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal development and transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "becoming."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otropic
    -0.70
    inately
    -0.69
    umbo
    -0.66
    pper
    -0.65
    been
    -0.65
    ramid
    -0.65
    duty
    -0.65
    udge
    -0.64
    issue
    -0.63
    top
    -0.63
    POSITIVE LOGITS
     accustomed
    0.95
     extinct
    0.92
     entangled
    0.88
     acquainted
    0.87
     obsolete
    0.86
     immersed
    0.84
     embroiled
    0.81
     disillusion
    0.80
     overwhelmed
    0.79
     aware
    0.79
    Act Density 0.021%

    No Known Activations