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

    Neuronpedia

    INDEX
    Explanations

    phrases enclosed in square brackets

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gors
    -0.67
     Finals
    -0.66
     reckoning
    -0.66
     Salem
    -0.64
     Phoenix
    -0.64
     Luck
    -0.63
     Chennai
    -0.63
     Britann
    -0.62
     cancell
    -0.61
     SAM
    -0.61
    POSITIVE LOGITS
    âĢ¦]
    1.61
    ...]
    1.51
    english
    1.12
    REDACTED
    0.96
    ']
    0.93
    ederal
    0.79
    !]
    0.78
    entimes
    0.78
    :]
    0.78
    ideshow
    0.78
    Act Density 0.032%

    No Known Activations