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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and verbs related to actions and associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĦst
    -0.15
    üzel
    -0.14
    ñana
    -0.14
    geist
    -0.14
    оло
    -0.14
    klä
    -0.14
    PRS
    -0.13
    Ix
    -0.13
    eful
    -0.13
    .DataBindings
    -0.13
    POSITIVE LOGITS
     preparation
    0.35
     Preparation
    0.32
     prepar
    0.32
     preparing
    0.31
     preparations
    0.31
     prepares
    0.30
     prepare
    0.29
    åĩĨå¤ĩ
    0.29
     prepared
    0.28
    Preparing
    0.27
    Act Density 0.008%

    No Known Activations