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

    Neuronpedia

    INDEX
    Explanations

    words related to steel and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.17
    draul
    -0.16
    phere
    -0.15
     Stealth
    -0.15
    eya
    -0.15
    dik
    -0.15
    permission
    -0.15
     Stein
    -0.15
     Flames
    -0.15
     stealth
    -0.14
    POSITIVE LOGITS
    workers
    0.30
    worker
    0.24
    licity
    0.24
    works
    0.24
    making
    0.23
     plate
    0.22
     wool
    0.21
    anguage
    0.21
    work
    0.20
    trap
    0.20
    Act Density 0.015%

    No Known Activations