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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant impact or reach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jed
    -0.15
    owitz
    -0.14
    pad
    -0.14
    thesis
    -0.14
    lemen
    -0.14
    ermen
    -0.14
    er
    -0.14
    ness
    -0.13
    asi
    -0.13
    isque
    -0.13
    POSITIVE LOGITS
    -going
    0.27
     going
    0.27
    going
    0.26
    -running
    0.25
     standing
    0.25
     reaching
    0.24
     running
    0.23
    -standing
    0.23
    running
    0.23
    Going
    0.23
    Act Density 0.091%

    No Known Activations