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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sensitive or confidential information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecake
    -0.64
    ULTS
    -0.62
     lane
    -0.61
    orio
    -0.61
    owered
    -0.60
     Pis
    -0.60
     potato
    -0.59
     Hatch
    -0.59
     Beard
    -0.59
     Bass
    -0.59
    POSITIVE LOGITS
    istic
    0.99
    ity
    0.98
    izes
    0.96
    izing
    0.93
    ized
    0.93
    isations
    0.90
    izations
    0.88
    ism
    0.88
    ities
    0.88
    ization
    0.87
    Act Density 0.020%

    No Known Activations