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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey relationships and interactions with various conditions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipa
    -0.16
    ipar
    -0.15
    辺
    -0.14
    uhn
    -0.14
    us
    -0.14
    APT
    -0.14
    roken
    -0.14
    ึà¸ģ
    -0.14
    лÑĥÑĩ
    -0.14
    HEST
    -0.14
    POSITIVE LOGITS
    rons
    0.16
     experience
    0.16
    翼
    0.15
     whom
    0.15
     terminal
    0.14
    mdp
    0.14
     problems
    0.14
     Problems
    0.14
     access
    0.14
     knowledge
    0.14
    Act Density 0.367%

    No Known Activations