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

    Neuronpedia

    INDEX
    Explanations

    strings of letters or numbers that follow a specific pattern

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    seys
    -1.08
    netflix
    -1.01
    ropolitan
    -0.83
    psons
    -0.81
    anguage
    -0.78
    CTV
    -0.77
    culosis
    -0.77
    indust
    -0.77
    packs
    -0.76
    ersive
    -0.75
    POSITIVE LOGITS
    xd
    0.81
     Hex
    0.76
     decisive
    0.76
     Mortal
    0.74
     defensively
    0.73
     contested
    0.72
    xe
    0.71
     finish
    0.69
     Kong
    0.69
     bounce
    0.69
    Act Density 0.026%

    No Known Activations