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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate frequency or dominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     både
    -0.16
     many
    -0.15
    ress
    -0.15
    alted
    -0.15
    asse
    -0.15
     slightest
    -0.15
    oren
    -0.14
    icum
    -0.14
    ivent
    -0.14
    mere
    -0.14
    POSITIVE LOGITS
     consists
    0.18
     ÑģоÑģÑĤоиÑĤ
    0.18
     concerned
    0.17
     consist
    0.17
     consisted
    0.16
    à¹Ĩ
    0.16
    äºĽ
    0.15
     comprised
    0.15
    yyyy
    0.15
     consisting
    0.15
    Act Density 0.071%

    No Known Activations