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

    Neuronpedia

    INDEX
    Explanations

    references to principles and values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gie
    -0.19
    ÙĪØ·
    -0.16
    ney
    -0.16
    akan
    -0.16
    reat
    -0.15
    itude
    -0.15
    elian
    -0.15
    ÑĢÑĥ
    -0.15
    NESS
    -0.15
    ropolis
    -0.14
    POSITIVE LOGITS
    -agent
    0.30
    ities
    0.24
     investigator
    0.22
    -Agent
    0.20
     Investig
    0.20
    ps
    0.19
    stown
    0.18
    pal
    0.18
    ized
    0.18
    /pr
    0.18
    Act Density 0.018%

    No Known Activations