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

    Neuronpedia

    INDEX
    Explanations

    numbers associated with statistics or quantities

    oai_token-act-pair · gpt-3.5-turbo

    the word "In" followed by numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hooks
    -0.75
     blasp
    -0.74
     ingred
    -0.72
     looms
    -0.68
     heir
    -0.67
     ens
    -0.64
     alias
    -0.63
     secrets
    -0.63
     sche
    -0.62
     ty
    -0.62
    POSITIVE LOGITS
    juries
    1.29
    jured
    1.22
     contrast
    1.19
    ventory
    1.13
    expensive
    1.12
     addition
    1.11
    cluding
    1.08
    flation
    1.05
    effective
    1.01
    jury
    1.00
    Act Density 0.207%

    No Known Activations