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

    Neuronpedia

    INDEX
    Explanations

    individuals or entities who are in positions of authority or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a person or entity responsible for a specific task or role

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.57
    oken
    -0.56
     Klux
    -0.54
    acceptable
    -0.54
    ¿½
    -0.54
    evin
    -0.54
    ashed
    -0.53
    adr
    -0.52
     Knot
    -0.52
    osponsors
    -0.52
    POSITIVE LOGITS
     of
    1.11
     overseeing
    1.00
     thereof
    0.95
    posts
    0.79
    of
    0.76
     OF
    0.74
    oft
    0.72
    OF
    0.71
    taker
    0.70
     Of
    0.67
    Act Density 0.077%

    No Known Activations