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

    Neuronpedia

    INDEX
    Explanations

    references to concepts, reasoning, hierarchy, and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +:+
    -0.56
     Züge
    -0.39
    adaptiveStyles
    -0.38
    ImageField
    -0.36
    кож
    -0.36
     sebou
    -0.36
     désolés
    -0.34
    野外
    -0.32
     לת
    -0.32
    我又
    -0.32
    POSITIVE LOGITS
    那就是
    1.24
     Namely
    1.05
     namely
    1.03
    namely
    0.97
     yaitu
    0.81
     yakni
    0.74
    それは
    0.71
     ovvero
    0.70
     iaitu
    0.70
     cioè
    0.66
    Act Density 0.288%

    No Known Activations