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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a limitation or state of being incomplete

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a sense of exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.70
    ongs
    -0.63
    tails
    -0.62
    iller
    -0.62
    didn
    -0.62
    CU
    -0.62
    none
    -0.61
    also
    -0.60
    alam
    -0.60
     MUST
    -0.59
    POSITIVE LOGITS
     marginally
    1.09
     scratching
    0.90
     accessible
    0.86
     moderately
    0.84
     halfway
    0.83
     partially
    0.82
     peripher
    0.82
     conceivable
    0.82
     half
    0.80
     mildly
    0.77
    Act Density 0.058%

    No Known Activations