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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their repeated usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -1.00
     themſelves
    -0.83
     himſelf
    -0.82
     itſelf
    -0.77
    */),
    -0.76
     lenker
    -0.75
    Demikian
    -0.75
    }';
    -0.74
     ―――――
    -0.74
     myſelf
    -0.73
    POSITIVE LOGITS
     I
    0.83
     you
    0.82
     everybody
    0.77
     they
    0.74
     we
    0.74
    2
    0.71
     it
    0.71
     everyone
    0.67
    And
    0.65
    1
    0.64
    Act Density 0.303%

    No Known Activations