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

    Neuronpedia

    INDEX
    Explanations

    references to social or political equality issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.37
    2:0.07
    3:0.03
    4:0.02
    5:0.06
    6:0.09
    7:0.05
    8:0.06
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    DragonMagazine
    -1.76
    ertodd
    -1.71
    NetMessage
    -1.69
    natureconservancy
    -1.65
     ACTIONS
    -1.53
    bley
    -1.45
     Ended
    -1.44
    ministic
    -1.43
    FTWARE
    -1.43
    prototype
    -1.40
    POSITIVE LOGITS
    ]
    4.23
    ?]
    4.09
    ']
    4.01
    ]:
    4.00
    ]"
    3.93
    …]
    3.89
    ],
    3.84
    ].
    3.81
    !]
    3.76
    .]
    3.61
    Act Density 0.106%

    No Known Activations