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

    Neuronpedia

    INDEX
    Explanations

    phrases related to assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "ab" indicating various forms of the word "abandon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancial
    -0.72
     Nadu
    -0.68
     Beir
    -0.68
     Cups
    -0.67
     Savior
    -0.65
    backer
    -0.65
     Schultz
    -0.65
    zsche
    -0.65
     Maker
    -0.64
     Sieg
    -0.63
    POSITIVE LOGITS
    bey
    1.04
    raham
    1.02
    stract
    1.00
    omination
    0.99
    usable
    0.98
    ject
    0.96
    rid
    0.94
    ibi
    0.92
    rog
    0.90
    ril
    0.88
    Act Density 0.017%

    No Known Activations