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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disclaimers and informational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xes
    -0.16
    ansi
    -0.16
     Mate
    -0.15
    hawks
    -0.15
    INTERFACE
    -0.14
    upe
    -0.14
     Preconditions
    -0.14
    ková
    -0.14
    PLIT
    -0.14
     Sanity
    -0.14
    POSITIVE LOGITS
     risk
    0.16
    risk
    0.15
     Goodman
    0.15
    LOB
    0.14
    ÏħÏĥ
    0.14
    arton
    0.14
     RID
    0.14
     drift
    0.14
    rij
    0.14
    FileSync
    0.14
    Act Density 0.026%

    No Known Activations