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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress and advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roys
    -0.16
     nearest
    -0.16
     CHUNK
    -0.15
    nearest
    -0.15
    defgroup
    -0.14
    би
    -0.14
    obile
    -0.14
    оÑĢи
    -0.14
    ouce
    -0.14
     far
    -0.14
    POSITIVE LOGITS
     within
    0.28
     Within
    0.26
    Within
    0.26
    within
    0.24
     Clo
    0.23
     inches
    0.23
     mere
    0.22
    Clo
    0.21
    clo
    0.20
     closing
    0.20
    Act Density 0.072%

    No Known Activations