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

    Neuronpedia

    INDEX
    Explanations

    terms related to algorithms and systems for selecting and ranking features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.65
    Portail
    -0.56
    Portale
    -0.55
    ########.
    -0.55
     varandra
    -0.53
    ExtendWith
    -0.53
     specchio
    -0.52
     effectivement
    -0.51
    RegisterType
    -0.51
     Meksiku
    -0.50
    POSITIVE LOGITS
     also
    0.83
     inoltre
    0.79
     moreover
    0.72
    UnusedPrivate
    0.70
    contentLoaded
    0.67
     همچنین
    0.62
     также
    0.60
     ayrıca
    0.59
     furthermore
    0.58
    Dabei
    0.57
    Act Density 0.475%

    No Known Activations