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

    Neuronpedia

    INDEX
    Explanations

    references to specific names or concepts related to internet platforms or company names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ambro
    -0.59
     Nielsen
    -0.55
     Entered
    -0.55
     Murdoch
    -0.49
     Hait
    -0.47
     interrupt
    -0.47
     cue
    -0.46
     convict
    -0.46
     overload
    -0.46
     bias
    -0.46
    POSITIVE LOGITS
    iverse
    0.70
    prototype
    0.63
    brids
    0.62
    ecycle
    0.60
    ignty
    0.60
    yssey
    0.59
    ertodd
    0.59
    gemony
    0.59
    stice
    0.58
    eworld
    0.58
    Act Density 1.874%

    No Known Activations