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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating logical clarity and coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &___
    -0.88
     ―――――
    -0.78
     esternos
    -0.78
     oprot
    -0.77
    uxxxx
    -0.76
    MigrationBuilder
    -0.76
     متعلقه
    -0.76
     myſelf
    -0.74
    migrationBuilder
    -0.73
     للمعارف
    -0.71
    POSITIVE LOGITS
     sense
    1.88
    sense
    1.55
     Sense
    1.27
     SENSE
    1.25
    Sense
    1.24
     sentido
    1.16
     senso
    0.96
     senses
    0.93
     sens
    0.90
    ense
    0.79
    Act Density 0.094%

    No Known Activations