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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "up" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tigny
    -0.63
     kelas
    -0.60
    jetbrains
    -0.58
     Moy
    -0.56
    atschapp
    -0.56
     BorderRadius
    -0.54
     régimen
    -0.54
     betale
    -0.53
    MeasureSpec
    -0.53
     rospy
    -0.52
    POSITIVE LOGITS
     themſelves
    0.81
    ']],
    0.81
    》.
    0.81
    Personensuche
    0.80
    '}),
    0.78
    }`).
    0.78
    "]);
    0.77
    '}';
    0.76
    )))
    0.76
     ſeveral
    0.75
    Act Density 0.007%

    No Known Activations