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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating challenges or issues related to experiences or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToAction
    -0.56
    GenerationType
    -0.55
    Trayectoria
    -0.53
    Enllaces
    -0.52
     Савезне
    -0.51
     '\\;'
    -0.51
    ngdoc
    -0.51
    getOut
    -0.49
     springfox
    -0.47
     setMessage
    -0.47
    POSITIVE LOGITS
     hitch
    0.77
     hic
    0.71
     nig
    0.70
     hang
    0.65
     negative
    0.62
     snag
    0.62
     complaint
    0.60
    TagMode
    0.60
     qual
    0.59
     irritant
    0.59
    Act Density 0.347%

    No Known Activations