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

    Neuronpedia

    INDEX
    Explanations

    action words related to starting something new or taking initiative

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launch" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Son
    -0.64
    emo
    -0.63
    Score
    -0.62
    enhagen
    -0.61
    verages
    -0.57
     entirety
    -0.57
    avering
    -0.57
    udes
    -0.56
    GO
    -0.56
    enza
    -0.55
    POSITIVE LOGITS
     anew
    1.07
    lishing
    0.84
    hement
    0.81
     INTO
    0.80
    pad
    0.77
    launch
    0.77
    escape
    0.75
    laun
    0.74
    eers
    0.73
    nings
    0.70
    Act Density 0.065%

    No Known Activations