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

    Neuronpedia

    INDEX
    Explanations

    words related to disappointment or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    instances of disappointment or negative sentiments expressed through the prefix "dis-."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetti
    -0.78
     Kinnikuman
    -0.77
    glers
    -0.75
     Reach
    -0.67
    eers
    -0.66
     Deer
    -0.64
     Kop
    -0.63
     Hedge
    -0.63
    akeru
    -0.63
     Kuh
    -0.63
    POSITIVE LOGITS
    ruption
    1.06
    cerning
    1.05
    cipl
    1.05
    cipline
    1.04
    comfort
    1.02
    rup
    1.01
    ordered
    1.00
    patch
    0.99
    placed
    0.99
    enfranch
    0.98
    Act Density 0.009%

    No Known Activations