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

    Neuronpedia

    INDEX
    Explanations

    the imperative form of verbs that suggest action or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.08
    4:0.09
    5:0.07
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
    phans
    -2.10
    ramid
    -2.07
     Memories
    -2.00
     Pandora
    -1.98
    ��
    -1.94
    Lost
    -1.93
    sbm
    -1.88
    amia
    -1.87
    �
    -1.85
     Pension
    -1.80
    POSITIVE LOGITS
    bys
    2.02
     industrialized
    1.97
     nort
    1.88
     Collider
    1.86
     hunters
    1.86
     empir
    1.85
     idiots
    1.84
     Australians
    1.81
     Europeans
    1.77
     hunter
    1.77
    Act Density 0.000%

    No Known Activations