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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and querying operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.67
    𝘃
    -0.65
    en
    -0.65
    ly
    -0.64
    man
    -0.61
    red
    -0.61
    re
    -0.61
    𝗸
    -0.60
    r
    -0.60
    mer
    -0.59
    POSITIVE LOGITS
     ་་
    1.19
     ſeveral
    1.00
     preſent
    1.00
     myſelf
    0.96
     Efq
    0.94
     itſelf
    0.94
     Majefty
    0.91
     purpoſe
    0.90
    uminum
    0.89
     Anſ
    0.88
    Act Density 0.023%

    No Known Activations