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

    Neuronpedia

    INDEX
    Explanations

    instances where someone or something is chosen or picked for a role or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "selected"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cre
    -0.68
     heels
    -0.68
    hur
    -0.67
    Net
    -0.67
    Jam
    -0.67
    ctrl
    -0.66
     sink
    -0.65
    olic
    -0.65
    pl
    -0.63
    plug
    -0.62
    POSITIVE LOGITS
     selections
    0.93
    selection
    0.91
     selected
    0.88
    selected
    0.86
     randomly
    0.86
     selection
    0.84
    ecided
    0.83
     selects
    0.82
    dinand
    0.81
     Selection
    0.79
    Act Density 0.013%

    No Known Activations