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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up or enrollment actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Broadway
    -0.14
    quet
    -0.14
    egr
    -0.14
    akter
    -0.14
    enda
    -0.13
     Altern
    -0.13
    gov
    -0.12
    amoto
    -0.12
     unders
    -0.12
    aille
    -0.12
    POSITIVE LOGITS
    angan
    0.15
    retch
    0.14
    OVÃģ
    0.14
    ategorical
    0.14
    ificantly
    0.14
     Reeves
    0.14
    abor
    0.14
     Lal
    0.13
    psilon
    0.13
    onia
    0.13
    Act Density 0.010%

    No Known Activations