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

    Neuronpedia

    INDEX
    Explanations

    active verbal directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.10
    3:0.07
    4:0.08
    5:0.07
    6:0.07
    7:0.09
    8:0.07
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
     £
    -2.05
    ($
    -2.04
     (£
    -2.01
     ($
    -1.90
     backs
    -1.90
    Graphics
    -1.88
    pmwiki
    -1.85
     $
    -1.83
    Str
    -1.80
     sideways
    -1.79
    POSITIVE LOGITS
    agos
    2.10
    vet
    2.08
    resent
    2.06
    iant
    1.99
    rican
    1.98
     ancest
    1.96
     Sanctuary
    1.92
    auna
    1.91
    sylv
    1.91
    uni
    1.91
    Act Density 0.000%

    No Known Activations