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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical instructions or references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ails" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neutral
    -0.75
     spe
    -0.62
     CB
    -0.61
     Proposition
    -0.60
     pat
    -0.59
     compar
    -0.58
     cow
    -0.58
     potential
    -0.58
     starting
    -0.58
     attribute
    -0.58
    POSITIVE LOGITS
    ails
    4.70
    ailed
    2.67
    ail
    2.61
    ailing
    2.51
    ailable
    1.76
    ILS
    1.34
    aults
    1.34
    tails
    1.31
    urses
    1.23
    mails
    1.20
    Act Density 0.010%

    No Known Activations