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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and adverbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing certainty or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussions
    -0.65
     Restoration
    -0.64
    ries
    -0.60
    dain
    -0.60
    rowth
    -0.60
     Dynamics
    -0.60
     Zel
    -0.60
    lete
    -0.58
     Admission
    -0.58
    cot
    -0.58
    POSITIVE LOGITS
    hett
    0.74
    ðŁ
    0.73
     tremend
    0.65
     understatement
    0.64
    iour
    0.64
     tha
    0.63
     shorth
    0.63
    cient
    0.62
     ðŁij
    0.61
    pport
    0.61
    Act Density 0.327%

    No Known Activations