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

    Neuronpedia

    INDEX
    Explanations

    the word "who", indicating a focus on individuals or subjects associated with actions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fair
    -0.16
    686
    -0.16
    wan
    -0.14
    scribe
    -0.14
    deo
    -0.13
    frog
    -0.13
    arna
    -0.13
     договоÑĢ
    -0.13
     caravan
    -0.13
     medio
    -0.13
    POSITIVE LOGITS
    eric
    0.16
    anton
    0.15
    ombat
    0.15
    hoff
    0.15
    oya
    0.15
    νοÏį
    0.14
    ieten
    0.13
    OURCE
    0.13
    stadt
    0.13
    rend
    0.13
    Act Density 0.026%

    No Known Activations