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

    Neuronpedia

    INDEX
    Explanations

    text related to actions, events, and processes that are ongoing or have occurred

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text block

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.78
    apo
    -0.60
    SPONSORED
    -0.59
    endi
    -0.55
    hang
    -0.55
     reper
    -0.53
    owitz
    -0.52
    ierre
    -0.52
    istries
    -0.52
    adan
    -0.52
    POSITIVE LOGITS
     aback
    0.81
    river
    0.79
    ream
    0.78
     )]
    0.75
    irect
    0.72
    escription
    0.71
    SourceFile
    0.65
    roid
    0.65
    own
    0.64
    rive
    0.63
    Act Density 0.166%

    No Known Activations