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

    Neuronpedia

    INDEX
    Explanations

    instances of past actions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    beiter
    -0.15
    iners
    -0.14
    GRAPH
    -0.14
    tra
    -0.14
    ettle
    -0.14
    ault
    -0.14
    aget
    -0.14
     {}:
    -0.14
    ollen
    -0.14
    boro
    -0.13
    POSITIVE LOGITS
    -www
    0.16
    ovny
    0.15
     Action
    0.15
     action
    0.14
     pros
    0.14
     a
    0.14
    Action
    0.14
     tons
    0.13
     Elim
    0.13
     Uns
    0.13
    Act Density 0.180%

    No Known Activations