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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating limitation or restriction on possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dill
    -0.64
     Torch
    -0.61
    est
    -0.61
    lich
    -0.61
    estern
    -0.59
     Dru
    -0.58
    esting
    -0.58
    ducers
    -0.58
     Mercer
    -0.57
    ded
    -0.57
    POSITIVE LOGITS
     speculate
    0.81
     afford
    0.79
     survive
    0.73
     marginally
    0.73
     cope
    0.70
    hiba
    0.66
     exacerbate
    0.66
     exist
    0.66
     dream
    0.66
    ICES
    0.66
    Act Density 0.067%

    No Known Activations