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

    Neuronpedia

    INDEX
    Explanations

    words relating to identity and representation in diverse social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edition
    -0.14
    udder
    -0.14
    mani
    -0.13
    irie
    -0.13
    ãĥ¼ãĥ«
    -0.13
     è¶
    -0.13
    esser
    -0.13
    alion
    -0.13
    ards
    -0.13
     Edition
    -0.13
    POSITIVE LOGITS
     yes
    0.59
     sure
    0.57
    yes
    0.50
     Yes
    0.46
    Yes
    0.45
     certainly
    0.44
     YES
    0.42
    sure
    0.41
     Sure
    0.40
     yeah
    0.38
    Act Density 0.136%

    No Known Activations