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

    Neuronpedia

    INDEX
    Explanations

    words related to social roles or membership within a group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tinyos
    -0.57
    muir
    -0.42
     Mom
    -0.42
    rimin
    -0.42
     rain
    -0.42
     Yards
    -0.41
     yards
    -0.40
    idon
    -0.40
     injure
    -0.40
     Yaw
    -0.40
    POSITIVE LOGITS
     toiminta
    0.56
    DockStyle
    0.54
     kardeş
    0.52
    ISupport
    0.50
     hyö
    0.49
    insegna
    0.45
     Савезне
    0.45
     päät
    0.44
     kysy
    0.44
    inerja
    0.44
    Act Density 0.159%

    No Known Activations