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

    Neuronpedia

    INDEX
    Explanations

    references to collective actions or memberships in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.91
     SwitchCompat
    -0.78
     ſche
    -0.76
     itſelf
    -0.76
     Monfieur
    -0.75
     cauſe
    -0.73
     Shakspeare
    -0.72
     himſelf
    -0.72
     purpoſe
    -0.72
     ſeveral
    -0.72
    POSITIVE LOGITS
     even
    0.79
     sogar
    0.65
    甚至是
    0.64
     may
    0.62
     chiar
    0.61
    even
    0.61
     mancher
    0.60
     some
    0.58
     אף
    0.58
     already
    0.57
    Act Density 0.441%

    No Known Activations