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

    Neuronpedia

    INDEX
    Explanations

    phrases related to certainty and urgency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words 'at' and 'it' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abundantly
    -0.68
     Aad
    -0.65
    è¦ļéĨĴ
    -0.64
     laun
    -0.62
     Lazarus
    -0.61
     Saber
    -0.61
     Odin
    -0.60
    berman
    -0.59
    MER
    -0.58
     Heard
    -0.58
    POSITIVE LOGITS
    iously
    1.37
    ious
    1.26
    eness
    1.22
    ities
    1.14
    ciating
    1.10
    ELY
    1.07
    hement
    0.98
    istration
    0.95
    itate
    0.94
    izing
    0.92
    Act Density 0.136%

    No Known Activations