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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and concepts related to embeddings and mappings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exploitation
    -0.15
    ezi
    -0.15
    oldem
    -0.15
     ë§ī
    -0.14
    uggest
    -0.14
    etzt
    -0.14
    ledon
    -0.13
    ANEL
    -0.13
     Orig
    -0.13
     Blank
    -0.13
    POSITIVE LOGITS
     admit
    0.27
     satisfy
    0.27
     satisfies
    0.24
     admits
    0.23
     sat
    0.23
    滿
    0.23
     satisfied
    0.22
    æºĢ
    0.21
     coinc
    0.21
     admitting
    0.21
    Act Density 0.104%

    No Known Activations