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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    repeated use of conjunctions, particularly "and" and "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IPM
    -0.68
    CHQ
    -0.64
     Bucc
    -0.62
     Electrical
    -0.61
    Mus
    -0.61
     Donation
    -0.61
     Cognitive
    -0.60
    hiba
    -0.59
    AMI
    -0.58
    Motor
    -0.57
    POSITIVE LOGITS
     elsewhere
    1.11
     abroad
    1.00
    orld
    0.81
     nowhere
    0.78
     Everywhere
    0.76
    âķIJ
    0.74
    anchester
    0.73
    ãģ¦
    0.73
    NOW
    0.72
    oké
    0.72
    Act Density 0.088%

    No Known Activations