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

    Neuronpedia

    INDEX
    Explanations

    verbs related to providing details or specifications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.83
    tic
    -0.74
    nin
    -0.71
    naissance
    -0.71
    cosystem
    -0.70
    jam
    -0.69
    aturated
    -0.68
    suits
    -0.64
    itans
    -0.64
    Exper
    -0.64
    POSITIVE LOGITS
     specifics
    1.59
     details
    1.11
     particulars
    1.09
     names
    0.99
     specific
    0.98
     nor
    0.95
     anything
    0.89
     exactly
    0.89
     exact
    0.88
     any
    0.86
    Act Density 0.158%

    No Known Activations