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

    Neuronpedia

    INDEX
    Explanations

    concepts related to abstract ideas and philosophical inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eming
    -0.16
     Rape
    -0.14
    ÑĢап
    -0.14
    .bel
    -0.14
    adin
    -0.14
    otel
    -0.13
     Lester
    -0.13
    ahl
    -0.13
    357
    -0.13
    vale
    -0.13
    POSITIVE LOGITS
     exactly
    0.20
     actually
    0.17
     entails
    0.17
     looks
    0.17
     mean
    0.17
     accompl
    0.16
    ooks
    0.16
    kke
    0.15
     Looks
    0.15
     might
    0.15
    Act Density 0.077%

    No Known Activations