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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer systems or software

    oai_token-act-pair · gpt-3.5-turbo

    mentions of systems or system-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urous
    -0.77
    tein
    -0.74
    onga
    -0.71
     earnest
    -0.69
    IELD
    -0.66
    ishable
    -0.64
    azo
    -0.64
    bow
    -0.61
    NF
    -0.61
     rib
    -0.61
    POSITIVE LOGITS
    atics
    1.30
    atically
    1.13
    atic
    1.01
     integ
    0.97
    wide
    0.95
    ologies
    0.93
    ically
    0.83
     architectures
    0.82
    ycle
    0.79
    ctl
    0.77
    Act Density 0.058%

    No Known Activations