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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions used in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.08
    2:0.06
    3:0.07
    4:0.06
    5:0.06
    6:0.07
    7:0.27
    8:0.05
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
    ategory
    -2.40
     withd
    -2.31
     concess
    -2.31
    again
    -2.30
     Prosecutors
    -2.22
    ecause
    -2.19
    norm
    -2.14
     taxp
    -2.08
    pmwiki
    -2.06
     Prosecut
    -2.02
    POSITIVE LOGITS
     envelope
    2.28
     transcript
    2.03
     laughter
    2.02
     allele
    1.96
    sburg
    1.94
     dove
    1.88
     adapter
    1.86
     foreskin
    1.83
    agus
    1.82
     chuckle
    1.82
    Act Density 0.000%

    No Known Activations