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

    Neuronpedia

    INDEX
    Explanations

    the word "sen" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sen" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heels
    -0.69
     Pwr
    -0.69
    anked
    -0.66
     hitch
    -0.66
    tails
    -0.65
     Mayweather
    -0.63
    cock
    -0.62
     juggling
    -0.61
     grounding
    -0.61
     tolerance
    -0.61
    POSITIVE LOGITS
    pai
    1.55
    egal
    1.14
    iors
    1.12
    seless
    1.10
    ocide
    1.07
    iture
    1.05
    vironment
    1.04
    escent
    1.00
    ior
    0.99
    ovo
    0.94
    Act Density 0.018%

    No Known Activations