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

    Neuronpedia

    INDEX
    Explanations

    words related to starting or beginning an action

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of starting or launching something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¢âĢ¢
    -0.67
    Bey
    -0.65
     Hipp
    -0.63
    este
    -0.63
    umbo
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    avering
    -0.60
     Extrem
    -0.58
    makers
    -0.58
    rooms
    -0.58
    POSITIVE LOGITS
    TAIN
    0.99
    uates
    0.91
    rative
    0.88
    chnology
    0.88
     anew
    0.82
     initi
    0.81
    arthed
    0.80
    uberty
    0.78
    aneously
    0.78
    phase
    0.77
    Act Density 0.021%

    No Known Activations