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

    Neuronpedia

    INDEX
    Explanations

    instances of coding terminology related to functions and classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alted
    -0.15
    asts
    -0.14
    ensed
    -0.14
    adox
    -0.14
    ishlist
    -0.14
    pill
    -0.14
    ç¤
    -0.13
    pun
    -0.13
     Vu
    -0.13
    oux
    -0.13
    POSITIVE LOGITS
     hello
    0.19
    .foo
    0.19
    /foo
    0.18
    foo
    0.18
    Foo
    0.18
     foo
    0.17
     some
    0.17
     another
    0.17
    _hello
    0.17
    42
    0.17
    Act Density 0.239%

    No Known Activations