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

    Neuronpedia

    INDEX
    Explanations

    occurrences where something goes wrong or there is a negative outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases that repeatedly use the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.74
    ahime
    -0.74
    idon
    -0.70
    lass
    -0.68
    align
    -0.66
    multipl
    -0.66
    hement
    -0.65
    ducers
    -0.64
    PK
    -0.63
    arthy
    -0.61
    POSITIVE LOGITS
     marginally
    0.99
     kidding
    0.94
     incidentally
    0.84
     spor
    0.81
     seconds
    0.80
     minutes
    0.79
     surpassed
    0.75
     vaguely
    0.74
     days
    0.72
     briefly
    0.72
    Act Density 0.066%

    No Known Activations