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

    Neuronpedia

    INDEX
    Explanations

    information or mentions related to confidentiality, anonymity, or speaking off the record

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ney
    -0.58
    charg
    -0.57
    tons
    -0.52
    abase
    -0.52
    cer
    -0.49
    nant
    -0.49
    nard
    -0.46
    RAM
    -0.44
     cider
    -0.44
    ONS
    -0.44
    POSITIVE LOGITS
     anonymity
    0.85
    ously
    0.67
     anonym
    0.65
     pseudonym
    0.57
     anonymously
    0.55
    ãĥĩ
    0.55
     Flavoring
    0.55
     afforded
    0.54
     shrouded
    0.52
    Downloadha
    0.51
    Act Density 10.444%

    No Known Activations