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

    Neuronpedia

    INDEX
    Explanations

    The main thing this neuron does is find specific triggering words that indicate the start of a new section or topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of conversational or narrative transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mate
    -0.63
     commun
    -0.62
     ',
    -0.60
     transc
    -0.60
     '.
    -0.59
     lit
    -0.57
     ILCS
    -0.55
     VIDE
    -0.55
     virgin
    -0.54
     cutter
    -0.54
    POSITIVE LOGITS
    Else
    0.83
    :(
    0.76
    hesda
    0.75
    mosp
    0.73
    APS
    0.72
    Weak
    0.71
    Jew
    0.67
    Pr
    0.66
    agar
    0.66
    auga
    0.66
    Act Density 0.147%

    No Known Activations