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

    Neuronpedia

    INDEX
    Explanations

    mathematical terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.17
     certain
    -0.15
    Narr
    -0.14
    antan
    -0.14
    aan
    -0.14
    ergy
    -0.14
    igit
    -0.13
     cannot
    -0.13
    iele
    -0.13
    ieg
    -0.13
    POSITIVE LOGITS
     Throughout
    0.28
     throughout
    0.27
    Throughout
    0.27
     convention
    0.26
    Convention
    0.23
     abusing
    0.23
     abuse
    0.22
     Convention
    0.22
     abused
    0.22
    notation
    0.21
    Act Density 0.194%

    No Known Activations