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

    Neuronpedia

    INDEX
    Explanations

    adverbs with the suffix "-ally" or "-ically"

    oai_token-act-pair · gpt-3.5-turbo

    adverbial forms that describe manner or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pirate
    -0.84
     Vikings
    -0.80
     Riders
    -0.78
     Vaj
    -0.72
     Payne
    -0.72
     Chiefs
    -0.71
     Moonlight
    -0.71
     TY
    -0.70
     Clive
    -0.70
     Meteor
    -0.69
    POSITIVE LOGITS
     speaking
    1.05
     minded
    1.00
     inclined
    0.81
    opt
    0.79
     transitioned
    0.79
     Speaking
    0.76
    speaking
    0.76
    tic
    0.75
     insured
    0.75
    tics
    0.74
    Act Density 0.036%

    No Known Activations