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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    possessive constructs and phrases indicating possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alties
    -0.79
    soever
    -0.75
    anes
    -0.62
    stocks
    -0.61
    igr
    -0.60
    aneers
    -0.60
    roit
    -0.59
    children
    -0.57
    igious
    -0.57
    trust
    -0.56
    POSITIVE LOGITS
     hoping
    1.07
     how
    1.05
     what
    0.97
     why
    0.95
     another
    0.92
     whats
    0.84
     excerpt
    0.82
     How
    0.76
     something
    0.76
     a
    0.75
    Act Density 0.050%

    No Known Activations