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

    Neuronpedia

    INDEX
    Explanations

    instances of the preposition "on" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.70
    illac
    -0.63
    rosso
    -0.62
    ©¶æ¥µ
    -0.60
    Types
    -0.59
     Secondly
    -0.59
    anged
    -0.59
    £ı
    -0.58
     Reincarn
    -0.58
    ãĤ¡
    -0.56
    POSITIVE LOGITS
     helpless
    0.89
     behalf
    0.88
    erous
    0.88
     approving
    0.76
     suspic
    0.75
    screen
    0.75
    ggle
    0.73
    etime
    0.72
    sighted
    0.70
     nostalg
    0.69
    Act Density 0.024%

    No Known Activations