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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "no"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    midt
    -0.81
    worn
    -0.66
    ulative
    -0.66
    ivic
    -0.66
    rored
    -0.63
    endish
    -0.63
    iership
    -0.63
    otton
    -0.61
    inarily
    -0.60
    erala
    -0.60
    POSITIVE LOGITS
    xious
    1.06
     matter
    1.02
     avail
    0.99
    terday
    0.94
     longer
    0.93
    ct
    0.93
    oooooooooooooooo
    0.85
     sooner
    0.83
    isy
    0.83
     harm
    0.83
    Act Density 0.068%

    No Known Activations