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

    Neuronpedia

    INDEX
    Explanations

    technical terms and names related to various fields like simulations, gravitational lenses, compressed stabilized earth blocks, malware aliases, programming languages, electric flow, rogue groups, and project names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific concepts and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.68
     confir
    -0.64
    olulu
    -0.62
     inclined
    -0.59
    hesda
    -0.59
     tempted
    -0.58
    jriwal
    -0.58
     plunged
    -0.58
     coerc
    -0.57
    iston
    -0.57
    POSITIVE LOGITS
    "—
    0.68
    LOCK
    0.66
    MAP
    0.61
     Boh
    0.60
    Bal
    0.60
    Alias
    0.58
     Bastard
    0.58
    ",
    0.57
     Patel
    0.57
    XXX
    0.57
    Act Density 0.407%

    No Known Activations