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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an expected outcome or intention

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Fine
    -0.74
    ILE
    -0.74
     Katy
    -0.74
     complicate
    -0.71
     Panic
    -0.71
     Indust
    -0.70
     Surprise
    -0.69
     Dism
    -0.69
     Stern
    -0.68
     Amateur
    -0.68
    POSITIVE LOGITS
     wont
    0.84
    Ont
    0.83
    alian
    0.81
    elf
    0.81
    burgh
    0.79
    ptr
    0.77
     existed
    0.75
     iP
    0.75
     regener
    0.73
    liner
    0.73
    Act Density 6.067%

    No Known Activations