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

    Neuronpedia

    INDEX
    Explanations

    commands or coding-related keywords

    oai_token-act-pair · gpt-3.5-turbo

    elements related to scripting, coding, or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.74
    untled
    -0.73
    autical
    -0.70
    isks
    -0.68
    lag
    -0.67
    istical
    -0.66
    cade
    -0.66
    chid
    -0.66
    urances
    -0.65
    ento
    -0.65
    POSITIVE LOGITS
    ©¶æ
    0.91
     alias
    0.81
    =""
    0.74
     Uri
    0.73
     Delete
    0.70
     Replace
    0.67
     pref
    0.65
     dun
    0.64
     tc
    0.64
     aliases
    0.63
    Act Density 0.311%

    No Known Activations