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

    Neuronpedia

    INDEX
    Explanations

    words related to the improvement or deterioration of situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating worsening or improving conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heid
    -0.74
    ellow
    -0.73
     entirety
    -0.70
    WB
    -0.65
    rans
    -0.64
    onement
    -0.62
    apple
    -0.62
    inance
    -0.61
    zhen
    -0.60
    vell
    -0.60
    POSITIVE LOGITS
     progressively
    0.87
     veter
    0.86
     nearer
    0.79
     acquainted
    0.77
    noticed
    0.73
     sidx
    0.73
     traction
    0.72
     gradually
    0.71
     creeps
    0.69
     accustomed
    0.69
    Act Density 0.105%

    No Known Activations