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

    Neuronpedia

    INDEX
    Explanations

    terms related to predictions and pre-defined conditions

    oai_token-act-pair · gpt-3.5-turbo

    words related to predictions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     twist
    -0.65
    BOX
    -0.63
    ASE
    -0.63
    Fra
    -0.62
    Hub
    -0.62
     Libre
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    IRO
    -0.60
    ierrez
    -0.60
     Wit
    -0.59
    POSITIVE LOGITS
    efined
    1.29
    nis
    1.05
    acent
    1.01
    icip
    0.99
    etermin
    0.98
    ominated
    0.97
    isp
    0.96
    icates
    0.95
    icated
    0.95
    awn
    0.95
    Act Density 0.019%

    No Known Activations