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

    Neuronpedia

    INDEX
    Explanations

    phrases related to success or achievement

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate processes or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereto
    -0.72
    orld
    -0.68
    farious
    -0.65
    osal
    -0.65
    ortium
    -0.64
    this
    -0.63
    perty
    -0.63
     therein
    -0.61
    estones
    -0.59
    olith
    -0.57
    POSITIVE LOGITS
     HUGE
    0.70
     Qiao
    0.70
    hift
    0.67
     alot
    0.66
     assuming
    0.66
    prisingly
    0.62
     Solitaire
    0.62
     Patreon
    0.61
    ï¸
    0.60
     doub
    0.59
    Act Density 0.309%

    No Known Activations