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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tidy
    -0.15
     next
    -0.15
    381
    -0.14
     NEXT
    -0.14
    olle
    -0.14
     latest
    -0.14
     Next
    -0.14
    _FP
    -0.13
    get
    -0.13
    iani
    -0.13
    POSITIVE LOGITS
     fact
    0.23
     way
    0.21
     kind
    0.20
     apart
    0.17
    kind
    0.17
     regard
    0.17
     reason
    0.16
     matter
    0.16
     factor
    0.16
    fact
    0.16
    Act Density 0.147%

    No Known Activations