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

    Neuronpedia

    INDEX
    Explanations

    the word "exact" when it appears with numerical values across various texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rift
    -0.89
    ker
    -0.87
    ipolar
    -0.82
     ashore
    -0.81
    ulton
    -0.80
    ublic
    -0.79
    NetMessage
    -0.77
     Pigs
    -0.76
    stown
    -0.75
    HS
    -0.75
    POSITIVE LOGITS
    itude
    1.07
     opposite
    0.99
     wording
    0.99
     embodiment
    0.97
    ions
    0.95
     same
    0.94
    aneous
    0.94
     amount
    0.92
    ing
    0.92
     exact
    0.92
    Act Density 7.585%

    No Known Activations