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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the act of communication

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sm
    -0.75
    uck
    -0.70
    comed
    -0.70
     Jub
    -0.69
    este
    -0.68
    eled
    -0.67
    nen
    -0.65
    toe
    -0.65
    ough
    -0.65
    720
    -0.65
    POSITIVE LOGITS
     communicates
    1.07
     communicated
    1.02
     communicating
    0.99
     behavi
    0.97
     communicate
    0.92
     communication
    0.92
    natureconservancy
    0.87
     newsp
    0.83
     vulner
    0.83
     Communication
    0.82
    Act Density 0.009%

    No Known Activations