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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "then" or related variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    横
    -0.15
    raci
    -0.15
    wig
    -0.14
    оÑĩнÑĭй
    -0.14
    але
    -0.14
     Kaplan
    -0.14
     PIN
    -0.13
    rap
    -0.13
    leh
    -0.13
    rab
    -0.13
    POSITIVE LOGITS
    iper
    0.15
    Fi
    0.15
    lamaz
    0.14
    iye
    0.14
     Sher
    0.14
    pulse
    0.14
    .***.***
    0.13
    çĽĸ
    0.13
     Fi
    0.13
    eto
    0.13
    Act Density 0.025%

    No Known Activations