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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interaction or connection between entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0002
    -0.79
    é¾
    -0.69
     Niet
    -0.68
    802
    -0.66
    IK
    -0.66
     DK
    -0.65
    dn
    -0.65
     Impossible
    -0.65
    402
    -0.64
    QL
    -0.64
    POSITIVE LOGITS
    selves
    0.93
    worldly
    0.91
    isphere
    0.78
    heric
    0.78
     individually
    0.77
    emonic
    0.76
    self
    0.75
    dayName
    0.72
     creatively
    0.70
    inant
    0.70
    Act Density 0.013%

    No Known Activations