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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "together."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Transparency
    -0.17
     Wich
    -0.16
    -anchor
    -0.15
    ibilit
    -0.15
    Å¡nÃŃ
    -0.15
    arrass
    -0.14
     Transparent
    -0.14
    LEAR
    -0.14
     prez
    -0.14
    ietet
    -0.14
    POSITIVE LOGITS
    point
    0.14
    ferences
    0.13
    byn
    0.13
     distracted
    0.13
    ioni
    0.13
     Ber
    0.13
    orte
    0.13
    /single
    0.13
    pu
    0.13
    q
    0.13
    Act Density 0.005%

    No Known Activations