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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change in topic or introducing a new perspective

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a transition or shift in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "},"
    -0.69
    cffff
    -0.61
    Americ
    -0.56
    elled
    -0.55
    iami
    -0.54
     CLSID
    -0.54
     respons
    -0.54
     guiActiveUnfocused
    -0.50
    osponsors
    -0.50
     estab
    -0.48
    POSITIVE LOGITS
    ,
    1.11
    ,.
    0.95
    ,,
    0.87
    ,...
    0.87
    âĢ¦
    0.87
    ...
    0.80
     though
    0.78
    .,
    0.78
     however
    0.78
    âĢ¦)
    0.77
    Act Density 0.119%

    No Known Activations