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

    Neuronpedia

    INDEX
    Explanations

    phrases related to documentaries or reports about specific events or people

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Priv
    -0.62
    warning
    -0.60
     Priv
    -0.58
    scribe
    -0.56
    priv
    -0.55
     distraction
    -0.54
    devices
    -0.52
     palate
    -0.52
     dictatorship
    -0.50
     Guinea
    -0.49
    POSITIVE LOGITS
    alian
    1.32
    chy
    1.29
    self
    1.21
    unes
    1.06
    alia
    1.00
    anium
    0.93
    ÃĥÃĤ
    0.93
    atic
    0.90
    asca
    0.90
     seems
    0.89
    Act Density 0.182%

    No Known Activations