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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "after" followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that indicate a sequence or event occurring after a specific incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orce
    -0.73
    ________________________________________________________________
    -0.66
     Chosen
    -0.66
    ogenic
    -0.66
    handler
    -0.65
    iction
    -0.64
    plane
    -0.64
    ologist
    -0.63
    favorite
    -0.63
    agram
    -0.62
    POSITIVE LOGITS
    ODUCT
    0.65
     Pew
    0.62
     discussions
    0.60
     backdrop
    0.59
     Bloomberg
    0.59
    PN
    0.59
     Garc
    0.59
    anmar
    0.58
     ..........
    0.58
     developments
    0.57
    Act Density 0.101%

    No Known Activations