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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-interest and social critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.98
     queſta
    -0.79
     insistent
    -0.77
     Thereafter
    -0.75
     conceivably
    -0.75
     totalled
    -0.74
     envisaged
    -0.72
     gripped
    -0.72
     whereupon
    -0.72
     envisage
    -0.71
    POSITIVE LOGITS
     dezelve
    0.43
     eenen
    0.32
     mode
    0.32
     connected
    0.32
    IAB
    0.29
     
    0.28
     kc
    0.28
     relative
    0.28
    theilung
    0.28
     previous
    0.27
    Act Density 0.616%

    No Known Activations