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

    Neuronpedia

    INDEX
    Explanations

    references to shoulders and related anatomical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hâte
    -0.79
    jarat
    -0.72
    #%%
    -0.71
     yrity
    -0.68
    tır
    -0.67
     trovar
    -0.65
    Portale
    -0.65
     Searle
    -0.63
     územ
    -0.63
     ouvriers
    -0.62
    POSITIVE LOGITS
     shoulders
    2.09
     shoulder
    2.09
     Shoulder
    1.99
    Shoulder
    1.81
    shoulder
    1.77
     Shoulders
    1.72
     Schulter
    1.36
     hombro
    1.32
     ombro
    1.30
     hombros
    1.25
    Act Density 0.090%

    No Known Activations