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

    Neuronpedia

    INDEX
    Explanations

    words related to changes in perception or stance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.89
    APH
    -0.75
    PU
    -0.68
     Brach
    -0.66
    ccoli
    -0.66
    staking
    -0.64
    gel
    -0.63
     Barron
    -0.63
    cade
    -0.63
    Consumer
    -0.61
    POSITIVE LOGITS
     tack
    0.98
     tune
    0.91
     wording
    0.91
     direction
    0.88
     course
    0.88
     diapers
    0.86
     name
    0.83
     diaper
    0.83
     complexion
    0.82
     allegiance
    0.81
    Act Density 0.097%

    No Known Activations