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

    Neuronpedia

    INDEX
    Explanations

    key concepts and important principles in scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     derivation
    -0.18
     determination
    -0.16
    lear
    -0.15
    athers
    -0.15
    áp
    -0.15
    426
    -0.14
     mant
    -0.14
     determin
    -0.14
     esp
    -0.14
    386
    -0.14
    POSITIVE LOGITS
     simpl
    0.19
     interesting
    0.18
     Ged
    0.17
     property
    0.17
     phenomena
    0.17
    interesting
    0.17
     Families
    0.17
     families
    0.16
    aran
    0.16
     PROPERTY
    0.16
    Act Density 0.114%

    No Known Activations