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

    Neuronpedia

    INDEX
    Explanations

    words related to experiences or emotions related to personal events and contemplation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    binary
    -0.76
    ussian
    -0.73
    rad
    -0.71
    ustom
    -0.70
     endeav
    -0.69
    ardless
    -0.68
    abouts
    -0.68
    mbuds
    -0.68
    mine
    -0.66
    ction
    -0.65
    POSITIVE LOGITS
    ³³³
    0.87
    ONSORED
    0.81
    ³³³³
    0.75
    Anyway
    0.75
     UPDATE
    0.73
    Until
    0.73
    UPDATE
    0.73
    Correction
    0.73
    Wr
    0.71
     Anyway
    0.69
    Act Density 0.394%

    No Known Activations