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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to abstract concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Redemption
    -0.15
    iÄħ
    -0.15
     Hunts
    -0.14
    ampp
    -0.14
    endon
    -0.14
    anzi
    -0.13
    ingly
    -0.13
    _EXTERN
    -0.13
    ugging
    -0.13
    anch
    -0.13
    POSITIVE LOGITS
    Å©
    0.16
    cheon
    0.15
    ihan
    0.15
    fty
    0.15
     notions
    0.15
    krom
    0.14
    avana
    0.14
    779
    0.14
    orgen
    0.14
    hoe
    0.14
    Act Density 0.031%

    No Known Activations