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

    Neuronpedia

    INDEX
    Explanations

    phrases related to eligibility or meeting specific criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meeting eligibility criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alps
    -0.69
     drip
    -0.68
     ende
    -0.67
     sleeve
    -0.64
     goodbye
    -0.64
     Gardens
    -0.63
     harb
    -0.63
     parting
    -0.61
     departure
    -0.61
     slit
    -0.61
    POSITIVE LOGITS
    ifies
    1.15
    ifications
    1.08
    ifying
    0.98
    ifiers
    0.96
     qualify
    0.91
    iotics
    0.87
    heses
    0.81
    ify
    0.81
    ifier
    0.81
    mma
    0.80
    Act Density 0.005%

    No Known Activations