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

    Neuronpedia

    INDEX
    Explanations

    connections between word frequency and significant events or themes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thrown
    -0.19
    provided
    -0.19
     penetrating
    -0.18
    thrown
    -0.18
     drawn
    -0.18
     Provided
    -0.17
     provided
    -0.17
    handled
    -0.16
    assage
    -0.16
     beaten
    -0.16
    POSITIVE LOGITS
     came
    0.34
     fell
    0.29
     became
    0.27
     went
    0.24
     began
    0.24
     rose
    0.23
     Came
    0.23
     grew
    0.22
    came
    0.22
     broke
    0.21
    Act Density 0.680%

    No Known Activations