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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals, particularly journalists and reporters, in a news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.14
    1:0.02
    2:0.02
    3:0.03
    4:0.25
    5:0.15
    6:0.05
    7:0.01
    8:0.13
    9:0.12
    10:0.01
    11:0.02
    Negative Logits
    ◼
    -2.12
     installed
    -1.96
     fulfill
    -1.89
     playbook
    -1.88
    ydia
    -1.87
     implement
    -1.84
     divest
    -1.82
     pledge
    -1.81
     execute
    -1.79
     declare
    -1.77
    POSITIVE LOGITS
    )—
    2.21
    }{
    2.17
    .")
    2.09
    dinand
    2.07
    )"
    2.05
    ...)
    2.03
    .)
    2.03
    })
    1.90
     Contribut
    1.89
    .)
    1.89
    Act Density 0.002%

    No Known Activations