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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "never."

    oai_token-act-pair · gpt-3.5-turbo

    phrases or statements involving the word "never."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.84
    ahime
    -0.71
    achev
    -0.70
     Tags
    -0.70
    iant
    -0.69
    lace
    -0.69
    iants
    -0.68
    redients
    -0.67
    States
    -0.66
    nah
    -0.65
    POSITIVE LOGITS
    theless
    1.58
     bothered
    1.05
     dreamed
    1.00
     existed
    0.82
     EVER
    0.82
     ceases
    0.80
     imagined
    0.79
     heard
    0.79
     hesitated
    0.78
     hesitate
    0.76
    Act Density 0.053%

    No Known Activations