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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring "ach"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drm
    -0.71
     kindly
    -0.68
     futures
    -0.68
     shipped
    -0.65
     Nicotine
    -0.64
     stocking
    -0.64
    ©¶æ
    -0.62
     schematic
    -0.61
     noses
    -0.61
     stacked
    -0.61
    POSITIVE LOGITS
    ach
    1.06
    annel
    1.06
    akra
    1.03
    ieving
    0.99
    idon
    0.94
    iev
    0.91
    ammed
    0.87
    ief
    0.87
    ten
    0.86
    apon
    0.85
    Act Density 0.012%

    No Known Activations