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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant changes, impacts, or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assis
    -0.15
    kie
    -0.14
    redient
    -0.14
     κÏį
    -0.14
    ech
    -0.14
    opup
    -0.13
    _portal
    -0.13
    avier
    -0.13
    zo
    -0.13
    Assert
    -0.13
    POSITIVE LOGITS
     when
    0.18
     chez
    0.16
    quam
    0.16
     directions
    0.16
    iasi
    0.16
    ijo
    0.15
     hos
    0.15
    ίκ
    0.15
    orte
    0.15
    .Directory
    0.14
    Act Density 0.171%

    No Known Activations