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

    Neuronpedia

    INDEX
    Explanations

    definitions of variable names in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stoll
    -0.83
    ]));
    -0.77
    hobo
    -0.75
     FANDOM
    -0.73
    <h6>
    -0.68
    )
    -0.68
    atever
    -0.67
    ¡¡
    -0.66
     fortun
    -0.65
     nicio
    -0.65
    POSITIVE LOGITS
     NAME
    1.51
     name
    1.47
     Name
    1.46
     names
    1.43
     Names
    1.36
    NAME
    1.31
    names
    1.30
    Name
    1.28
    name
    1.27
     getName
    1.24
    Act Density 0.111%

    No Known Activations