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

    Neuronpedia

    INDEX
    Explanations

    phrases related to getting back on track or returning to a previous state

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to getting back on track or recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.95
    Interstitial
    -0.76
    Plot
    -0.69
    ghai
    -0.68
    imon
    -0.68
    ially
    -0.67
     WATCHED
    -0.66
     Donation
    -0.64
     likened
    -0.63
     Transfer
    -0.63
    POSITIVE LOGITS
     haunt
    0.86
     whence
    0.79
     quarters
    0.71
     shore
    0.71
     civilisation
    0.70
     forth
    0.69
    apons
    0.68
     Gaia
    0.67
     Asgard
    0.67
     vengeance
    0.66
    Act Density 0.074%

    No Known Activations