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

    Neuronpedia

    INDEX
    Explanations

    imperative phrases and prompts that encourage action or creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amespace
    -0.17
     вÑģ
    -0.15
    OrNil
    -0.14
    ere
    -0.14
    kind
    -0.14
     Kind
    -0.13
    ores
    -0.13
     kond
    -0.13
     èŃ
    -0.13
     Rouge
    -0.13
    POSITIVE LOGITS
    wick
    0.18
     Go
    0.18
     enjoy
    0.17
    Enjoy
    0.17
     Enjoy
    0.17
     enjoyment
    0.16
     LET
    0.15
    tsky
    0.15
     GO
    0.15
    piration
    0.15
    Act Density 0.160%

    No Known Activations