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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "end" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ney
    -0.17
    kills
    -0.16
    assis
    -0.16
    thing
    -0.15
    аннÑĸ
    -0.15
    agh
    -0.15
     breeze
    -0.14
    ìĦľëĬĶ
    -0.14
    888
    -0.14
    neys
    -0.14
    POSITIVE LOGITS
    ow
    0.19
    orse
    0.18
    owment
    0.18
    /end
    0.17
    orses
    0.17
    ear
    0.17
    æķ¦
    0.17
    ocrin
    0.16
    /start
    0.15
    owed
    0.15
    Act Density 0.042%

    No Known Activations