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

    Neuronpedia

    INDEX
    Explanations

    architectural terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lling
    -0.84
    ted
    -0.76
    lli
    -0.76
    NRS
    -0.76
    ting
    -0.76
    nder
    -0.75
    Tube
    -0.74
    vec
    -0.74
    instein
    -0.72
    ties
    -0.69
    POSITIVE LOGITS
    itect
    1.44
    ocobo
    0.94
    osaurs
    0.85
    ief
    0.83
    opoulos
    0.80
    ottesville
    0.79
    arity
    0.79
    ipel
    0.79
    ipation
    0.78
    andise
    0.78
    Act Density 0.053%

    No Known Activations