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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or mentions of "another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    انيف
    -0.74
     chofe
    -0.74
     ſche
    -0.73
     purpoſe
    -0.72
     étoient
    -0.72
     whoſe
    -0.70
     normaux
    -0.70
    icana
    -0.69
     Pergamon
    -0.69
     MainAxisSize
    -0.69
    POSITIVE LOGITS
    太
    0.65
     Too
    0.65
    巨
    0.64
     too
    0.62
    مح
    0.59
    Too
    0.57
    ngh
    0.56
     quite
    0.56
    雄
    0.56
     太
    0.56
    Act Density 0.160%

    No Known Activations