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

    Neuronpedia

    INDEX
    Explanations

    statements related to global impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to societal groups and global issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lopp
    -0.61
    uristic
    -0.57
    reshold
    -0.54
    umn
    -0.54
    á½
    -0.54
    tein
    -0.53
    Reloaded
    -0.52
    ãĤ·ãĥ£
    -0.51
    ikarp
    -0.51
    LOCK
    -0.51
    POSITIVE LOGITS
     alike
    1.96
     respectively
    1.55
     thereof
    1.22
     versa
    1.06
     thereto
    1.00
     accordingly
    0.98
     therein
    0.95
     thereafter
    0.83
     consequ
    0.80
     attRot
    0.79
    Act Density 0.534%

    No Known Activations