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

    Neuronpedia

    INDEX
    Explanations

    phrases related to access and availability of resources or information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↵
    -0.44
     den
    -0.44
    <?
    -0.43
     kies
    -0.42
     @
    -0.41
     "
    -0.41
     U
    -0.41
     unknownFields
    -0.41
     it
    -0.41
    kle
    -0.40
    POSITIVE LOGITS
     للاسماء
    0.85
    ^(@)
    0.81
     الرياضيه
    0.78
    \{\\
    0.74
    writeField
    0.73
     Pyrene
    0.69
    StoryboardSegue
    0.69
     pleaſure
    0.69
     Arp
    0.68
     IBRARY
    0.68
    Act Density 0.378%

    No Known Activations