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

    Neuronpedia

    INDEX
    Explanations

    references to processes involving flow or movement through various mediums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IBOutlet
    -0.46
     Lingkungan
    -0.45
    jenigen
    -0.42
     lisäksi
    -0.39
     autour
    -0.39
    Thrown
    -0.39
    disposing
    -0.38
     voldo
    -0.38
     fråga
    -0.38
    hawatir
    -0.37
    POSITIVE LOGITS
     hindurch
    0.95
     channels
    0.73
     paces
    0.70
     heen
    0.63
     motions
    0.62
     lens
    0.61
     hoops
    0.61
    ought
    0.59
     thick
    0.59
     tunnels
    0.58
    Act Density 0.188%

    No Known Activations