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

    Neuronpedia

    INDEX
    Explanations

    terms related to espionage or Spanish words

    oai_token-act-pair · gpt-3.5-turbo

    references to espionage and related entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.84
    TPPStreamerBot
    -0.73
    âķIJâķIJ
    -0.72
    roads
    -0.71
    DragonMagazine
    -0.71
    umeric
    -0.71
     compuls
    -0.68
    SpaceEngineers
    -0.68
    ĸļ
    -0.68
    =-=-=-=-
    -0.67
    POSITIVE LOGITS
    ionage
    1.22
    resso
    1.19
     Esp
    1.12
    encer
    0.86
    inia
    0.82
    lance
    0.80
    irit
    0.80
    inal
    0.79
    ano
    0.79
    inel
    0.78
    Act Density 0.008%

    No Known Activations