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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public involvement or interest

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people and their actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     predecessor
    -0.65
     successor
    -0.63
    Completed
    -0.51
    sche
    -0.50
     operative
    -0.49
    ãĥ¼ãĥĨ
    -0.49
     {*
    -0.48
    abus
    -0.48
     denotes
    -0.47
     operator
    -0.47
    POSITIVE LOGITS
     theirs
    0.69
     alike
    0.69
     themselves
    0.67
     their
    0.64
    selves
    0.60
     flock
    0.57
     clam
    0.57
     collectively
    0.57
     THEIR
    0.57
    joice
    0.54
    Act Density 1.989%

    No Known Activations