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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sealing actions or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to seals, both in terms of the animal and the act of sealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enhagen
    -0.75
    nis
    -0.73
    itters
    -0.70
     Drawn
    -0.69
    llor
    -0.68
    icularly
    -0.68
    enburg
    -0.64
    sen
    -0.64
    asma
    -0.62
    rian
    -0.62
    POSITIVE LOGITS
    lock
    0.90
     sealing
    0.83
     sealed
    0.83
    keeper
    0.82
    recy
    0.82
     seal
    0.79
    rets
    0.79
    keeping
    0.76
     seals
    0.75
    wrap
    0.74
    Act Density 0.059%

    No Known Activations