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

    Neuronpedia

    INDEX
    Explanations

    words associated with film reviews and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     famously
    -0.20
    åıĺå¾Ĺ
    -0.15
    ustum
    -0.15
     곧
    -0.14
    igest
    -0.14
    /includes
    -0.14
     unr
    -0.14
    usercontent
    -0.13
     later
    -0.13
     ending
    -0.13
    POSITIVE LOGITS
     billed
    0.19
    }elseif
    0.16
     bills
    0.16
     Excell
    0.16
     certainly
    0.16
    }());↵
    0.16
     disappoint
    0.15
    /Area
    0.14
     arrived
    0.14
     seems
    0.14
    Act Density 0.121%

    No Known Activations