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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    sections of the document that are empty or contain no significant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.81
    /-
    -0.52
     Aber
    -0.50
     Shutterstock
    -0.47
     Peb
    -0.47
    lihood
    -0.47
    soever
    -0.46
     Goldstein
    -0.44
    /#
    -0.44
    ::::::::
    -0.43
    POSITIVE LOGITS
    ropolis
    0.56
    istani
    0.52
    tymology
    0.48
    uterte
    0.48
    ificate
    0.47
    icide
    0.47
    act
    0.47
    igrants
    0.46
    ocity
    0.46
    utenberg
    0.46
    Act Density 0.719%

    No Known Activations