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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gaining popularity or attention

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appoint
    -0.69
    osta
    -0.64
    odka
    -0.60
     exited
    -0.60
     ens
    -0.59
     completes
    -0.58
     manip
    -0.58
     checkpoints
    -0.58
     closure
    -0.57
     eas
    -0.56
    POSITIVE LOGITS
    roads
    1.29
    effic
    1.09
     academia
    1.05
     vitro
    1.05
    clusions
    1.05
     Europe
    1.02
     relation
    1.01
     lieu
    1.01
     regards
    1.00
    efficiency
    0.99
    Act Density 0.432%

    No Known Activations