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

    Neuronpedia

    INDEX
    Explanations

    website URLs containing certain keywords or phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ferr
    -0.89
    staking
    -0.84
    tails
    -0.72
    fully
    -0.71
     Aless
    -0.70
     Decay
    -0.69
     Nost
    -0.67
    FUL
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    MENT
    -0.65
    POSITIVE LOGITS
    zyk
    1.09
    ulhu
    1.07
    emonic
    0.96
    owell
    0.94
    ouls
    0.94
    ohl
    0.92
    ocalypse
    0.91
    arser
    0.89
    nl
    0.85
    alm
    0.85
    Act Density 0.239%

    No Known Activations