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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing continuity or extensive connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Everything
    -0.14
    aps
    -0.13
    wer
    -0.13
    053
    -0.13
    iges
    -0.13
    elik
    -0.13
    illac
    -0.13
    edb
    -0.13
    代
    -0.12
    ÅĻich
    -0.12
    POSITIVE LOGITS
     all
    0.71
     ALL
    0.44
    	all
    0.43
    =all
    0.42
    .all
    0.41
    all
    0.40
    (all
    0.40
     вÑģе
    0.38
    éĥ½
    0.37
     wszyst
    0.36
    Act Density 0.133%

    No Known Activations