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

    Neuronpedia

    INDEX
    Explanations

    first person plural pronouns followed by verbs or expressions indicating action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rowe
    -0.71
    states
    -0.66
    uates
    -0.66
    ocl
    -0.64
    forms
    -0.64
    grave
    -0.63
    rising
    -0.61
    personal
    -0.60
     Warrant
    -0.59
    cells
    -0.59
    POSITIVE LOGITS
    're
    1.19
    IRD
    1.10
    bsite
    1.00
    ird
    1.00
    'll
    0.97
    've
    0.96
    athered
    0.95
     ourselves
    0.94
    asel
    0.94
    asley
    0.90
    Act Density 0.195%

    No Known Activations