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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negotiations or agreements

    oai_token-act-pair · gpt-3.5-turbo

    commas and other punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertain
    -0.84
    hov
    -0.84
    scribe
    -0.71
    uce
    -0.71
    inar
    -0.66
     Activities
    -0.62
    è£ħ
    -0.61
    elf
    -0.59
    iven
    -0.59
    yon
    -0.59
    POSITIVE LOGITS
     albeit
    1.18
     citing
    1.15
     noting
    1.05
     stating
    1.00
     namely
    0.98
     though
    0.98
     saying
    0.97
     preferring
    0.96
     although
    0.96
     however
    0.95
    Act Density 0.330%

    No Known Activations