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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bocca
    -0.60
    ejs
    -0.54
     détruit
    -0.53
     espont
    -0.51
     amélior
    -0.50
     épu
    -0.50
     parlant
    -0.50
     indé
    -0.50
     ouvertes
    -0.50
     boire
    -0.49
    POSITIVE LOGITS
    唯一的
    0.83
     eneste
    0.81
    唯一
    0.75
    MemoryWarning
    0.74
     einzige
    0.70
     einzigen
    0.69
     sole
    0.69
     jedin
    0.66
     only
    0.65
    unico
    0.65
    Act Density 0.324%

    No Known Activations