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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing plans or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ="../../
    -0.50
     V
    -0.45
    пия
    -0.42
    ries
    -0.42
    amani
    -0.41
     cesse
    -0.40
    wyd
    -0.39
    MessageTagHelper
    -0.38
     D
    -0.38
     do
    -0.38
    POSITIVE LOGITS
     envisaged
    0.97
     planned
    0.97
     already
    0.94
    already
    0.93
    +#+#
    0.90
     Already
    0.90
     tentatively
    0.90
     ALREADY
    0.89
    SequentialGroup
    0.89
    Already
    0.87
    Act Density 0.349%

    No Known Activations