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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to processes and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unp
    -0.15
     Watts
    -0.14
    essenger
    -0.14
    ubar
    -0.14
     accommodation
    -0.14
    bones
    -0.13
    ìĤ¬íķŃ
    -0.13
    ks
    -0.13
     ready
    -0.13
    FFE
    -0.13
    POSITIVE LOGITS
    edo
    0.15
    uru
    0.15
    403
    0.14
    ãĤīãģĽ
    0.14
    oken
    0.14
    LOPT
    0.14
    _specific
    0.14
    edu
    0.14
    inium
    0.14
    mate
    0.13
    Act Density 0.079%

    No Known Activations