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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating attainment or receipt of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndef
    -0.17
    AndGet
    -0.17
    Current
    -0.16
    oz
    -0.15
    roken
    -0.15
    oth
    -0.14
    hoo
    -0.14
    izzas
    -0.14
    oon
    -0.14
    ented
    -0.14
    POSITIVE LOGITS
     rid
    0.35
    chas
    0.31
    tings
    0.23
    aways
    0.22
    cha
    0.19
    away
    0.19
     hold
    0.18
    tin
    0.18
    ElementsByTagName
    0.17
    -away
    0.17
    Act Density 0.133%

    No Known Activations