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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or connections between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mitt
    -0.14
    jeme
    -0.14
    ĶåĽŀ
    -0.14
    RuleContext
    -0.13
    ehler
    -0.13
    reate
    -0.13
    ãĥĨãĥ«
    -0.13
    xab
    -0.13
    .PerformLayout
    -0.13
    cassert
    -0.12
    POSITIVE LOGITS
     what
    0.18
     how
    0.17
     certain
    0.16
     those
    0.15
     the
    0.15
     precisely
    0.14
     potential
    0.14
     things
    0.13
    how
    0.13
     exactly
    0.13
    Act Density 0.501%

    No Known Activations