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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and modal verbs indicating potential actions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    utex
    -0.16
    icari
    -0.15
    HEY
    -0.15
    ustum
    -0.15
    Latch
    -0.15
    uppy
    -0.15
    ìķ¼
    -0.15
    çon
    -0.14
    /DTD
    -0.14
    POSITIVE LOGITS
     themselves
    0.23
     cr
    0.20
     dro
    0.19
     tell
    0.18
     probably
    0.18
     gas
    0.18
     tro
    0.17
     modest
    0.17
    arg
    0.16
     be
    0.16
    Act Density 0.073%

    No Known Activations