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

    Neuronpedia

    INDEX
    Explanations

    descriptions of character depth and emotional complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĽ
    -0.15
     Civic
    -0.14
    odash
    -0.14
     eup
    -0.14
    frame
    -0.14
    phia
    -0.14
    quier
    -0.14
     Kültür
    -0.13
    intptr
    -0.13
    .googleapis
    -0.13
    POSITIVE LOGITS
     flesh
    0.30
     complex
    0.23
     sympathetic
    0.22
     believable
    0.22
     multid
    0.22
     rel
    0.22
     Flesh
    0.21
     realistic
    0.21
    Complex
    0.21
     flawed
    0.21
    Act Density 0.129%

    No Known Activations