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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a sense of community or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    serrat
    -0.17
    utenberg
    -0.15
    ingo
    -0.15
    abbo
    -0.14
    awl
    -0.14
     Hole
    -0.14
    ignKey
    -0.14
    peare
    -0.14
    á»į
    -0.13
    ibold
    -0.13
    POSITIVE LOGITS
    nd
    0.16
    -temp
    0.15
     INTERRUPTION
    0.14
     Ratings
    0.14
    icle
    0.14
    erer
    0.14
    own
    0.14
    lay
    0.14
    lesen
    0.13
     Beat
    0.13
    Act Density 0.282%

    No Known Activations