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

    Neuronpedia

    INDEX
    Explanations

    exact details or specifics within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "exactly" and its variations, indicating precise information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULTS
    -0.71
    BSD
    -0.70
    MRI
    -0.64
    ework
    -0.64
    roe
    -0.63
    very
    -0.61
     moderately
    -0.61
     Tome
    -0.61
     immensely
    -0.60
    IRO
    -0.60
    POSITIVE LOGITS
     how
    0.85
     HOW
    0.84
    why
    0.83
     WHY
    0.81
     why
    0.79
    omething
    0.79
    what
    0.76
     whats
    0.74
     transpired
    0.71
    ifications
    0.70
    Act Density 0.031%

    No Known Activations