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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that something has already been done or in existence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or status of something existing or being established

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    case
    -0.83
    udge
    -0.82
    istics
    -0.81
    rary
    -0.80
    onnaissance
    -0.76
    Reviewer
    -0.73
    rent
    -0.71
    ueller
    -0.71
    orie
    -0.70
    usal
    -0.70
    POSITIVE LOGITS
     exists
    0.89
     existed
    0.89
     underway
    0.86
     fulfilled
    0.78
     surpassed
    0.77
     knew
    0.76
     gone
    0.75
     notor
    0.73
     begun
    0.73
     served
    0.72
    Act Density 0.030%

    No Known Activations