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

    Neuronpedia

    INDEX
    Explanations

    phrases related to accountability and support structures within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.19
    eme
    -0.18
    emetery
    -0.16
    elow
    -0.15
    etti
    -0.15
    nova
    -0.15
    erc
    -0.15
    echa
    -0.14
    quam
    -0.14
    onis
    -0.14
    POSITIVE LOGITS
    reds
    0.21
    cott
    0.17
    rippling
    0.17
     accountable
    0.16
    retch
    0.16
    marks
    0.16
    hold
    0.16
     sway
    0.15
    rics
    0.15
     Hold
    0.15
    Act Density 0.069%

    No Known Activations