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

    Neuronpedia

    INDEX
    Explanations

    phrases related to something that is unchanging or unchallenged

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unchanging or static concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MFT
    -0.73
     Dragonbound
    -0.67
     Reaper
    -0.67
     nurs
    -0.66
    igans
    -0.65
    ption
    -0.65
     Attribution
    -0.65
     reconciliation
    -0.62
    姫
    -0.61
     CLSID
    -0.61
    POSITIVE LOGITS
    icle
    0.89
    agons
    0.86
    icks
    0.78
    arter
    0.77
    ropolis
    0.77
    kers
    0.77
    idian
    0.76
    alm
    0.75
    onne
    0.74
    ubes
    0.74
    Act Density 0.036%

    No Known Activations