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

    Neuronpedia

    INDEX
    Explanations

    references to file paths and directory structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¥
    -0.16
    norm
    -0.15
     prior
    -0.15
    zu
    -0.14
    éĨ´
    -0.14
    isia
    -0.13
    oul
    -0.13
    errs
    -0.13
    oug
    -0.13
     GenerationType
    -0.13
    POSITIVE LOGITS
    _here
    0.22
    here
    0.20
    WithMany
    0.18
    _you
    0.16
    Guy
    0.16
    InThe
    0.16
    _HERE
    0.16
    ToDelete
    0.15
     stuff
    0.15
    çīĮ
    0.15
    Act Density 0.087%

    No Known Activations