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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical outcomes and operational metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     v
    -0.45
    BoxShadow
    -0.41
    delta
    -0.41
    dra
    -0.40
     Leg
    -0.39
    leg
    -0.39
    IMM
    -0.39
    .
    -0.39
     ostro
    -0.39
    mstyle
    -0.38
    POSITIVE LOGITS
     houſe
    0.98
     itſelf
    0.96
     Efq
    0.96
     Majefty
    0.96
     pleaſure
    0.92
     ſtate
    0.91
     Reſ
    0.91
     Jefus
    0.91
     Diſ
    0.90
     myſelf
    0.90
    Act Density 0.896%

    No Known Activations