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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oven
    -0.14
    irk
    -0.14
    ermalink
    -0.14
    .inflate
    -0.14
    gewater
    -0.13
    gren
    -0.13
    ->{_
    -0.13
    trs
    -0.13
    yar
    -0.13
    quir
    -0.13
    POSITIVE LOGITS
    iyah
    0.16
    tas
    0.15
    ì¹Ń
    0.15
    omatic
    0.14
    ibu
    0.14
    èħ°
    0.14
    å½¹
    0.14
     Dude
    0.13
     compass
    0.13
     crown
    0.13
    Act Density 0.151%

    No Known Activations