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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical compounds and processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "not" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAM
    -0.73
     contention
    -0.59
    ngth
    -0.58
     lightly
    -0.57
     affidav
    -0.57
     prevention
    -0.57
    tips
    -0.55
    hammer
    -0.55
    Pause
    -0.55
     Pigs
    -0.54
    POSITIVE LOGITS
    ronics
    1.18
    ronic
    1.15
    rix
    1.13
    rophic
    1.08
    rans
    1.03
    ainer
    1.02
    ories
    1.00
    rical
    0.97
    ools
    0.97
    ron
    0.96
    Act Density 0.045%

    No Known Activations