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

    Neuronpedia

    INDEX
    Explanations

    mentions related to terms of service or offers

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific non-standard character or token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.81
     fragmentation
    -0.68
     relocation
    -0.64
     Pwr
    -0.62
     Samar
    -0.62
     gloom
    -0.61
     Lunch
    -0.61
     Dirt
    -0.61
    osate
    -0.59
     stabilization
    -0.58
    POSITIVE LOGITS
    âĢķ
    0.87
    say
    0.87
    ¹
    0.83
    must
    0.83
    have
    0.82
    acca
    0.81
    could
    0.81
    º
    0.79
    should
    0.79
    âĸº
    0.78
    Act Density 0.108%

    No Known Activations