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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opportunities and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brill
    -0.17
    ç©
    -0.15
     brilliant
    -0.14
     Brilliant
    -0.14
     Maria
    -0.14
    eka
    -0.14
    å£
    -0.14
    è¥
    -0.14
    ää
    -0.14
    loh
    -0.14
    POSITIVE LOGITS
     divers
    0.20
     vpn
    0.20
     popis
    0.19
     Å
    0.18
    isme
    0.18
    vpn
    0.17
     comma
    0.17
     vs
    0.17
    resse
    0.17
     vt
    0.16
    Act Density 0.019%

    No Known Activations