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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or key terms associated with plans, methods, and categorical descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bh
    -0.15
    ÑĢоÑģÑĤо
    -0.15
    atu
    -0.15
    .dm
    -0.14
     pÅĻiÄįemž
    -0.14
    RIPTION
    -0.14
    Když
    -0.14
    ANNOT
    -0.14
    `\
    -0.13
    oned
    -0.13
    POSITIVE LOGITS
    /or
    0.24
     alike
    0.23
     importantly
    0.16
    orre
    0.16
    quot
    0.16
    rogen
    0.15
    uml
    0.15
    ersen
    0.15
    ampp
    0.14
     others
    0.14
    Act Density 0.317%

    No Known Activations