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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-awareness and personal growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γκα
    -0.17
    ]âĢı
    -0.15
    .nr
    -0.15
    LETTE
    -0.15
    antha
    -0.15
    Ton
    -0.15
    lluminate
    -0.14
    nze
    -0.14
    kp
    -0.14
    ække
    -0.14
    POSITIVE LOGITS
     Escort
    0.17
     Masc
    0.16
    205
    0.16
    boom
    0.15
    ube
    0.14
     Wah
    0.14
    plex
    0.14
     escort
    0.14
    ,
    0.14
     interpretation
    0.14
    Act Density 1.847%

    No Known Activations