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

    Neuronpedia

    INDEX
    Explanations

    terms related to guidance or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kili
    -0.15
    ipo
    -0.15
    å¬
    -0.15
    FRING
    -0.15
    urple
    -0.15
    lias
    -0.14
    lamaz
    -0.14
    ipple
    -0.14
    ocs
    -0.14
    iad
    -0.14
    POSITIVE LOGITS
    -direct
    0.15
    볬
    0.14
     Kushner
    0.14
    orrent
    0.14
     Gareth
    0.14
    ä¼į
    0.14
     Cah
    0.13
    ":"'
    0.13
     mee
    0.13
    shint
    0.13
    Act Density 0.025%

    No Known Activations