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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sis
    -0.19
    ritch
    -0.18
    rosso
    -0.18
    ses
    -0.17
    uld
    -0.16
     early
    -0.15
    yonel
    -0.15
    sst
    -0.15
    ós
    -0.15
    sel
    -0.14
    POSITIVE LOGITS
    -than
    0.34
    ally
    0.33
     than
    0.29
    _than
    0.28
    ality
    0.27
    than
    0.26
    -stage
    0.25
     stages
    0.23
     THAN
    0.23
    ALLY
    0.22
    Act Density 0.024%

    No Known Activations