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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific parts or sections of something

    oai_token-act-pair · gpt-3.5-turbo

    references to roles or positions within a group or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.85
    aukee
    -0.80
    ICO
    -0.79
    ãĤ´ãĥ³
    -0.75
    lishes
    -0.72
    jriwal
    -0.69
     Rampage
    -0.68
    ccording
    -0.65
     Despair
    -0.65
    hammad
    -0.65
    POSITIVE LOGITS
     eyed
    0.74
    osphere
    0.73
    lights
    0.67
    ales
    0.63
     closest
    0.62
     furthe
    0.59
    als
    0.57
     nearest
    0.57
     guy
    0.56
    iverse
    0.56
    Act Density 0.182%

    No Known Activations