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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irement
    -0.68
    akable
    -0.67
    ament
    -0.67
    ueless
    -0.65
     Yourself
    -0.65
    iona
    -0.64
    Submit
    -0.63
    istry
    -0.62
    kw
    -0.62
    clad
    -0.61
    POSITIVE LOGITS
    76561
    0.77
    asio
    0.76
     goodbye
    0.71
     bout
    0.69
     thats
    0.68
    rh
    0.66
     CrossRef
    0.65
     paraph
    0.64
     Cantor
    0.64
     congr
    0.63
    Act Density 0.092%

    No Known Activations