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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "agg" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "agg" or related terms emphasizing aggregation or gathering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defenders
    -0.71
     graphene
    -0.67
    phrine
    -0.66
     birth
    -0.64
     passage
    -0.63
     Gemini
    -0.63
    ©¶æ
    -0.62
     conditional
    -0.61
     candle
    -0.60
    )].
    -0.58
    POSITIVE LOGITS
    agg
    1.08
    regate
    1.02
    iott
    1.00
    idy
    0.90
    rieved
    0.90
    ernaut
    0.84
    irlf
    0.84
    regation
    0.84
    abba
    0.82
    ////
    0.82
    Act Density 0.007%

    No Known Activations