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

    Neuronpedia

    INDEX
    Explanations

    the word "Con" and its variations, indicating a focus on content concerning consequences, conclusions, or conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arp
    -0.15
    ña
    -0.15
    ritt
    -0.15
    cellent
    -0.15
    ENDING
    -0.14
    ensive
    -0.14
    Console
    -0.14
    ypad
    -0.14
    folio
    -0.14
    entimes
    -0.14
    POSITIVE LOGITS
    enen
    0.19
    aire
    0.17
    radi
    0.16
    exus
    0.16
    imbus
    0.15
    stan
    0.15
    tra
    0.15
    rig
    0.14
     prompt
    0.14
    nelly
    0.14
    Act Density 0.028%

    No Known Activations