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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing determination or commitment to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.70
    interstitial
    -0.69
    significant
    -0.67
    etheus
    -0.67
    piring
    -0.65
    Untitled
    -0.64
    ync
    -0.64
    pires
    -0.62
    iru
    -0.60
    uria
    -0.60
    POSITIVE LOGITS
     whatever
    1.17
     whichever
    1.11
    whatever
    0.99
     accordingly
    0.95
     alright
    0.94
     wherever
    0.89
     anyways
    0.87
     whoever
    0.83
     okay
    0.83
     accordance
    0.79
    Act Density 0.433%

    No Known Activations