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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant changes or pivotal moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    缼
    -0.16
    loat
    -0.14
    IRD
    -0.14
     éŁ³
    -0.14
    ihil
    -0.14
    gressor
    -0.14
    à¥ĭश
    -0.14
    irty
    -0.13
    iego
    -0.13
    êµIJ
    -0.13
    POSITIVE LOGITS
    iras
    0.15
     Naj
    0.15
     earned
    0.15
    elo
    0.14
     Ghost
    0.14
    ghost
    0.14
     ghost
    0.14
     mer
    0.14
    ppers
    0.14
     fault
    0.14
    Act Density 0.007%

    No Known Activations