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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recommendations and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ="{!!
    -0.17
    Macro
    -0.16
     Macro
    -0.16
    Æł
    -0.15
    rubu
    -0.15
    icontrol
    -0.15
    Angles
    -0.15
     imperson
    -0.14
    macro
    -0.14
    ledi
    -0.14
    POSITIVE LOGITS
     coinc
    0.15
    oha
    0.15
    iers
    0.15
     Vers
    0.15
    rou
    0.15
    isd
    0.14
    oland
    0.14
    Vers
    0.14
    ipc
    0.14
    olic
    0.14
    Act Density 0.189%

    No Known Activations