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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCHMARK
    -0.15
    rowned
    -0.15
    *sp
    -0.14
     imposs
    -0.14
    ШÐIJ
    -0.14
    ÐļТ
    -0.14
    оÑĥ
    -0.14
    å»
    -0.14
    FF
    -0.13
    rawer
    -0.13
    POSITIVE LOGITS
     certainly
    0.28
     may
    0.24
     aside
    0.23
    ?
    0.20
     isn
    0.20
    may
    0.19
     definitely
    0.19
     ведÑĮ
    0.19
     deserved
    0.18
     wasn
    0.18
    Act Density 0.216%

    No Known Activations