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

    Neuronpedia

    INDEX
    Explanations

    phrases related to staying united or together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obligations or demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Specific
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
     unden
    -0.57
     Adin
    -0.56
    Built
    -0.56
    د
    -0.56
     destro
    -0.56
    çĶ°
    -0.55
    ãĥ´
    -0.55
    Ùħ
    -0.53
    POSITIVE LOGITS
    âĦ¢
    0.91
    !,
    0.85
     syndrome
    0.85
    !
    0.74
     Syndrome
    0.71
    ®
    0.69
    !:
    0.67
     Productions
    0.67
    !.
    0.64
     ®
    0.62
    Act Density 0.681%

    No Known Activations