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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "recently."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "recently."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.79
    anza
    -0.74
    umption
    -0.73
    sure
    -0.73
    uming
    -0.72
     Bucket
    -0.71
    eers
    -0.71
    amination
    -0.70
     Donation
    -0.70
    adata
    -0.68
    POSITIVE LOGITS
    å¹
    0.81
     updated
    0.81
     renovated
    0.79
     announced
    0.78
     discovered
    0.77
     surpassed
    0.76
     bumped
    0.76
     seen
    0.75
     undergone
    0.75
     published
    0.75
    Act Density 0.031%

    No Known Activations