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

    Neuronpedia

    INDEX
    Explanations

    the verb "go" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    ania
    -1.92
     indict
    -1.90
     Mysteries
    -1.84
     Sinai
    -1.83
     reimb
    -1.82
     unravel
    -1.80
     bloodshed
    -1.76
     incompet
    -1.75
    aign
    -1.73
    rament
    -1.71
    POSITIVE LOGITS
    quartered
    2.20
     Tee
    2.12
    TPS
    2.08
    tube
    1.90
     Watt
    1.88
     ├
    1.88
    \">
    1.87
    ��
    1.87
    ð
    1.87
     contrad
    1.86
    Act Density 0.000%

    No Known Activations