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

    Neuronpedia

    INDEX
    Explanations

    terms related to correspondences and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    うちに
    -0.62
    heça
    -0.58
    abord
    -0.57
    hdashline
    -0.55
    NUMX
    -0.54
     $_[
    -0.54
    Bissau
    -0.54
    chargez
    -0.53
    — 
    -0.53
    etheless
    -0.53
    POSITIVE LOGITS
     corresponding
    1.45
     corrispond
    1.37
    corresponding
    1.35
     corresponds
    1.27
     equivalent
    1.26
     corris
    1.25
     equivalents
    1.25
     Correspond
    1.23
     counterpart
    1.22
     Corresponding
    1.20
    Act Density 0.419%

    No Known Activations