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

    Neuronpedia

    INDEX
    Explanations

    phrases related to flying

    oai_token-act-pair · gpt-3.5-turbo

    references to flying objects or the act of flying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.78
    é¾į
    -0.77
    xy
    -0.76
    liga
    -0.74
    ãĥ¤
    -0.74
    uary
    -0.74
    onal
    -0.72
    FINE
    -0.72
     Cumber
    -0.71
    ãĥİ
    -0.70
    POSITIVE LOGITS
    plane
    0.99
     reptiles
    0.89
     Sau
    0.85
    walk
    0.83
    walking
    0.82
    planes
    0.81
    walker
    0.80
     overhead
    0.79
     insects
    0.78
    hawk
    0.77
    Act Density 0.015%

    No Known Activations