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

    Neuronpedia

    INDEX
    Explanations

    words containing the sequence "ak" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    terms related to a specific type of character or persona, often represented by the pattern 'ak'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.78
    ãĤ¡
    -0.74
    ãĤ£
    -0.65
    ORPG
    -0.63
     pint
    -0.63
     Collider
    -0.61
    ãĤ§
    -0.61
     Fenrir
    -0.60
     ILCS
    -0.60
     Tempest
    -0.60
    POSITIVE LOGITS
    unin
    1.17
    arak
    1.13
    ota
    1.06
    umar
    1.06
    ihara
    0.99
    ansas
    0.98
    sha
    0.97
    arta
    0.94
    rish
    0.91
    shi
    0.91
    Act Density 0.028%

    No Known Activations