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

    Neuronpedia

    INDEX
    Explanations

    future tense verbs and their use in narratives or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earn
    -0.09
    .scalablytyped
    -0.08
    utex
    -0.08
    .ManyToMany
    -0.08
    ersh
    -0.07
    访
    -0.07
     ifndef
    -0.07
    lavÃŃ
    -0.07
    ìķ¼
    -0.07
    že
    -0.07
    POSITIVE LOGITS
     tell
    0.14
     tells
    0.11
     themselves
    0.10
     telling
    0.10
     agree
    0.10
     Tell
    0.10
     arg
    0.10
    Tell
    0.09
     argument
    0.09
    tell
    0.09
    Act Density 0.027%

    No Known Activations