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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of statements or commands in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Merid
    -0.78
     Chit
    -0.75
     Zand
    -0.72
    퀀
    -0.72
     entanto
    -0.72
     Hamb
    -0.72
     myth
    -0.69
    shub
    -0.63
     SwitchCompat
    -0.63
     épar
    -0.62
    POSITIVE LOGITS
    })).
    1.27
    expandindo
    1.26
    ').
    1.23
    ])).
    1.23
    ()).
    1.22
    ))).
    1.20
    )).
    1.20
    }`).
    1.19
    __).
    1.18
    ']").
    1.17
    Act Density 0.115%

    No Known Activations