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

    Neuronpedia

    INDEX
    Explanations

    phrases containing "if" to signify conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases or statements indicating uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤª
    -0.68
    rosse
    -0.65
    heimer
    -0.63
    iery
    -0.62
    FTWARE
    -0.61
    roid
    -0.61
    ashes
    -0.60
     Sons
    -0.59
    eland
    -0.59
    akia
    -0.59
    POSITIVE LOGITS
    fy
    0.89
    rame
    0.86
    tar
    0.76
     anything
    0.73
     you
    0.72
    yip
    0.69
    acebook
    0.68
     ya
    0.67
     necessary
    0.66
    lov
    0.64
    Act Density 0.094%

    No Known Activations