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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and their relationships in theoretical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilia
    -0.17
    933
    -0.15
    lech
    -0.14
     vera
    -0.14
     Blank
    -0.14
    ette
    -0.14
     Haut
    -0.14
    empl
    -0.14
     bott
    -0.13
    _userdata
    -0.13
    POSITIVE LOGITS
     can
    0.21
     general
    0.19
     naturally
    0.19
     turns
    0.19
     lead
    0.19
     appeared
    0.17
    turn
    0.17
     was
    0.17
     recieved
    0.16
    rew
    0.15
    Act Density 0.110%

    No Known Activations