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

    Neuronpedia

    INDEX
    Explanations

    statements regarding legal or career actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to legal proceedings and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eps
    -0.58
    atters
    -0.54
    hub
    -0.53
     Decoder
    -0.52
    mination
    -0.51
     unison
    -0.51
    earch
    -0.51
     reviewer
    -0.50
    selves
    -0.49
     Rosenstein
    -0.49
    POSITIVE LOGITS
     himself
    0.81
     stint
    0.65
     befriend
    0.65
     teammates
    0.62
     girlfriend
    0.62
     fian
    0.61
     classmates
    0.59
     fiance
    0.59
     fluent
    0.58
     quitting
    0.58
    Act Density 1.297%

    No Known Activations