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

    Neuronpedia

    INDEX
    Explanations

    references to going back to a particular point in time

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific formatting or markers typically used in structured content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.74
    EStream
    -0.73
    ihad
    -0.71
    BILITY
    -0.69
     constitu
    -0.68
    ©¶æ¥µ
    -0.65
     understatement
    -0.63
    è¦ļéĨĴ
    -0.63
     thin
    -0.62
    lled
    -0.61
    POSITIVE LOGITS
    door
    1.18
    ward
    1.10
    lash
    0.98
    stairs
    0.97
    wards
    0.90
    quartered
    0.88
    bringing
    0.87
    stage
    0.84
     Together
    0.83
    ership
    0.83
    Act Density 0.072%

    No Known Activations