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

    Neuronpedia

    INDEX
    Explanations

    terms related to communication and accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Exped
    -0.16
    ning
    -0.16
    icity
    -0.16
    uggage
    -0.16
     comedy
    -0.15
    GER
    -0.15
     lan
    -0.14
    çĦ¶
    -0.14
    à¸Ńย
    -0.14
     comps
    -0.14
    POSITIVE LOGITS
    wealth
    0.30
    iqué
    0.23
    orative
    0.22
    auté
    0.19
    unist
    0.19
    asurable
    0.19
    places
    0.19
    prise
    0.18
    tee
    0.18
    ercial
    0.18
    Act Density 0.020%

    No Known Activations