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

    Neuronpedia

    INDEX
    Explanations

    references to lists and enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gn
    -0.15
    uja
    -0.15
    ox
    -0.15
    prit
    -0.14
     Bias
    -0.14
    atu
    -0.14
    bias
    -0.14
    dera
    -0.14
    illis
    -0.14
    geh
    -0.14
    POSITIVE LOGITS
    ALLED
    0.17
    ÅĻes
    0.16
    reich
    0.15
    edly
    0.15
    incinn
    0.14
     Dort
    0.14
    omy
    0.14
    ÏĦÏį
    0.14
    ози
    0.14
    '])?
    0.13
    Act Density 0.001%

    No Known Activations