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

    Neuronpedia

    INDEX
    Explanations

    economic predictions or potential impacts

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     copying
    -0.75
     inspecting
    -0.69
     learns
    -0.69
     typed
    -0.67
    ophile
    -0.66
     Uses
    -0.66
    afety
    -0.65
     Noir
    -0.65
     guessing
    -0.64
     Palest
    -0.64
    POSITIVE LOGITS
     dissu
    1.34
     overshadow
    1.28
     deter
    1.18
     damp
    1.17
     outweigh
    1.14
     motivate
    1.12
     preclude
    1.12
     diminish
    1.11
     compel
    1.11
     discourage
    1.11
    Act Density 0.252%

    No Known Activations