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

    Neuronpedia

    INDEX
    Explanations

    keywords related to school safety and characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĻ
    -0.17
    екаÑĢ
    -0.15
     bif
    -0.15
    .Slf
    -0.15
     dikke
    -0.15
     reli
    -0.14
    .AF
    -0.14
     bil
    -0.14
    ¤í
    -0.14
    .Companion
    -0.13
    POSITIVE LOGITS
     Rangers
    0.25
     ranger
    0.22
     Ranger
    0.22
     Power
    0.22
     Sent
    0.21
    Power
    0.20
     morph
    0.20
     sent
    0.19
    morph
    0.18
     SENT
    0.18
    Act Density 0.008%

    No Known Activations