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

    Neuronpedia

    INDEX
    Explanations

    mentions of technology, websites, and digital services

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Attach
    -0.73
    uty
    -0.63
    ãĤ·ãĥ£
    -0.63
     srfAttach
    -0.57
    Completed
    -0.57
    ¿½
    -0.56
    REDACTED
    -0.53
     Pelosi
    -0.52
    ãĥ¯ãĥ³
    -0.51
    idth
    -0.51
    POSITIVE LOGITS
     willingly
    0.99
    their
    0.96
     because
    0.91
     bandwagon
    0.90
     sooner
    0.89
     differently
    0.88
     gladly
    0.87
     themselves
    0.86
     enthusiastically
    0.84
    selves
    0.84
    Act Density 0.860%

    No Known Activations