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

    Neuronpedia

    INDEX
    Explanations

    phrases with repeated or similar words

    oai_token-act-pair · gpt-3.5-turbo

    common occurrence of the word "the" in textual instructions or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.81
    Malley
    -0.73
    AFP
    -0.70
    wat
    -0.66
     Hezbollah
    -0.65
     Shiite
    -0.64
     Hussein
    -0.64
    .''
    -0.63
     nonetheless
    -0.63
     miscar
    -0.62
    POSITIVE LOGITS
    ses
    1.32
     same
    1.23
     aforementioned
    1.17
     entirety
    1.13
     respective
    1.13
     remainder
    1.10
     simplest
    1.08
     following
    1.08
     entire
    1.06
     latest
    1.06
    Act Density 0.848%

    No Known Activations