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

    Neuronpedia

    INDEX
    Explanations

    references to expertise and qualifications in professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Form
    -0.18
     Fighters
    -0.17
     Fetish
    -0.17
     Faul
    -0.16
     Fak
    -0.16
     Feld
    -0.16
     Fog
    -0.15
     Fortress
    -0.15
     Fitzgerald
    -0.15
    hos
    -0.15
    POSITIVE LOGITS
     filed
    0.52
     ï
    0.50
     fi
    0.48
     fe
    0.41
    fi
    0.39
    ï
    0.38
     fie
    0.35
    -file
    0.33
    file
    0.32
     el
    0.32
    Act Density 0.078%

    No Known Activations