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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a purpose or reason behind an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _UNUSED
    -0.14
    endif
    -0.14
    angu
    -0.14
    iske
    -0.14
    erner
    -0.14
    ÏĮν
    -0.14
     اÙĨد
    -0.14
    asts
    -0.13
    aea
    -0.13
    алÑĥ
    -0.13
    POSITIVE LOGITS
     fun
    0.25
     kicks
    0.23
    aging
    0.21
     FUN
    0.20
    _fun
    0.20
    Fun
    0.20
     granted
    0.20
     Fun
    0.19
     sport
    0.19
     pleasure
    0.18
    Act Density 0.160%

    No Known Activations