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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vengeance
    -0.67
    âĶĢâĶĢ
    -0.63
     Helsinki
    -0.63
     Atom
    -0.62
     Eleven
    -0.62
     Elena
    -0.60
    ãĥİ
    -0.59
     Irma
    -0.59
     Madagascar
    -0.59
     Rebirth
    -0.58
    POSITIVE LOGITS
    kinson
    1.05
    sell
    1.04
    cock
    1.01
    enson
    0.99
    ison
    0.99
    nick
    0.95
    rington
    0.94
    kens
    0.92
    rell
    0.91
    cz
    0.90
    Act Density 0.143%

    No Known Activations