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

    Neuronpedia

    INDEX
    Explanations

    words related to morphology or morphological terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to morphological characteristics and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HI
    -0.78
    äºĶ
    -0.77
    ILLE
    -0.74
    ×Ļ
    -0.72
     FW
    -0.71
    FORE
    -0.71
    âĸ¬
    -0.70
     Peb
    -0.69
     Nero
    -0.69
    ndra
    -0.66
    POSITIVE LOGITS
    orph
    1.27
    ophon
    1.26
    ological
    1.16
    istani
    1.04
    ogen
    1.02
    ozo
    0.99
    ologic
    0.98
    oes
    0.98
    s
    0.95
    ologically
    0.94
    Act Density 0.034%

    No Known Activations