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

    Neuronpedia

    INDEX
    Explanations

    text related to technical materials or physical locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to materials, structures, and specific items or concepts within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNCH
    -0.71
    astern
    -0.71
    ctor
    -0.71
    ELF
    -0.62
    ASED
    -0.62
    ected
    -0.62
    outhern
    -0.61
    pport
    -0.60
    XT
    -0.60
    chnology
    -0.59
    POSITIVE LOGITS
    s
    2.92
    sburg
    1.68
    sie
    1.55
    sb
    1.49
    ski
    1.47
    sis
    1.42
    sf
    1.38
    sburgh
    1.37
    sch
    1.35
    sg
    1.32
    Act Density 0.640%

    No Known Activations