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

    Neuronpedia

    INDEX
    Explanations

    words related to questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    })*/
    -0.60
    }))
    -0.57
    ſelves
    -0.54
     pleaſure
    -0.50
    rungsseite
    -0.50
    jspb
    -0.49
     للمعارف
    -0.47
     fédé
    -0.47
    }));
    -0.47
     ProtoMessage
    -0.47
    POSITIVE LOGITS
    que
    0.60
     galaxy
    0.57
     rectangle
    0.56
     Galaxy
    0.54
    vars
    0.53
    Rectangle
    0.52
     Rectangle
    0.52
     vars
    0.51
     Cotton
    0.49
    во
    0.49
    Act Density 0.287%

    No Known Activations