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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polk
    -0.65
    Tweet
    -0.65
     dstg
    -0.64
     Priv
    -0.63
    Flight
    -0.60
    Management
    -0.59
     Eleven
    -0.58
     Firefly
    -0.58
    å½
    -0.58
    Crew
    -0.57
    POSITIVE LOGITS
     involves
    1.40
     reflects
    1.23
     occurs
    1.20
     coincides
    1.18
     relates
    1.18
     signifies
    1.17
     arises
    1.17
     happens
    1.13
     hurts
    1.10
     represents
    1.10
    Act Density 0.292%

    No Known Activations