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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical specifications or consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to system conditions and instabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    htaking
    -0.57
    ©¶æ
    -0.56
     Philips
    -0.55
     acron
    -0.51
    ĸļ
    -0.50
    vine
    -0.49
     nutshell
    -0.49
    uli
    -0.49
     lately
    -0.48
    \":
    -0.47
    POSITIVE LOGITS
     wiser
    0.66
     altogether
    0.66
     indefinitely
    0.66
     anyway
    0.63
     forever
    0.63
    morrow
    0.62
     permanently
    0.61
     downstream
    0.60
     poorer
    0.58
     worthless
    0.58
    Act Density 1.566%

    No Known Activations