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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate rankings or lists of items and attributes related to health and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illions
    -0.15
     RuntimeObject
    -0.14
     preferring
    -0.14
    âĹİ
    -0.13
     Duffy
    -0.13
    oriented
    -0.12
     RuntimeMethod
    -0.12
     무ìĹĩ
    -0.12
     #+#
    -0.12
     scoped
    -0.12
    POSITIVE LOGITS
     Reasons
    0.29
     reasons
    0.27
     Ways
    0.26
     Things
    0.25
     Signs
    0.24
     ways
    0.23
     Must
    0.23
     must
    0.23
     Lesser
    0.22
     signs
    0.21
    Act Density 0.068%

    No Known Activations