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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "his"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     çĶŁåij½åij¨æľŁåĩ½æķ°
    -0.17
    åī¯
    -0.14
    天åłĤ
    -0.14
    ÐĴÑĤ
    -0.14
    affen
    -0.14
    iculos
    -0.14
    mort
    -0.13
    ÚĨار
    -0.13
    hec
    -0.13
     archit
    -0.13
    POSITIVE LOGITS
     return
    0.20
     arrival
    0.18
     demise
    0.18
     appearance
    0.17
     emergence
    0.17
     receipt
    0.17
     att
    0.17
     use
    0.17
     success
    0.16
    urf
    0.16
    Act Density 0.070%

    No Known Activations