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

    Neuronpedia

    INDEX
    Explanations

    instances of significant changes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rott
    -0.15
     Baum
    -0.15
    phere
    -0.15
    Leaks
    -0.14
    podob
    -0.14
    urga
    -0.14
     lifetime
    -0.14
     dim
    -0.14
    like
    -0.14
    reak
    -0.14
    POSITIVE LOGITS
    ableObject
    0.20
     inval
    0.17
    ouri
    0.16
    Evaluator
    0.15
    emailer
    0.15
     Grat
    0.15
    vore
    0.14
    _pending
    0.14
     grat
    0.14
    Ñħов
    0.14
    Act Density 0.015%

    No Known Activations