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

    Neuronpedia

    INDEX
    Explanations

    quotations or emphasized statements starting with special characters like an arrow or dash

    oai_token-act-pair · gpt-3.5-turbo

    the character 'ľ' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mirage
    -0.75
     reflex
    -0.67
     clitor
    -0.67
     mounts
    -0.65
     peripheral
    -0.64
     Gemini
    -0.63
     Okin
    -0.62
     trail
    -0.61
     pleasures
    -0.60
     leaps
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.25
    ternity
    0.92
    uthor
    0.89
    $
    0.85
    amily
    0.85
    \-
    0.83
    §
    0.82
    #$
    0.82
    Û
    0.81
    âĶĢâĶĢ
    0.79
    Act Density 0.191%

    No Known Activations