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

    Neuronpedia

    INDEX
    Explanations

    terminology related to nuclear weapons and treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reper
    -0.85
     declass
    -0.84
     confisc
    -0.80
     persecuted
    -0.75
     persecut
    -0.75
     assass
    -0.72
     rescuing
    -0.72
     sidx
    -0.72
     captives
    -0.71
     Fukushima
    -0.70
    POSITIVE LOGITS
    erson
    0.74
     Melody
    0.70
     Brush
    0.68
    ritten
    0.68
    riter
    0.68
     itch
    0.67
     Cherokee
    0.66
    inct
    0.66
     Experience
    0.65
    ois
    0.64
    Act Density 0.139%

    No Known Activations