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

    Neuronpedia

    INDEX
    Explanations

    mention of various plans and planning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .gdx
    -0.18
    angelo
    -0.17
    aceous
    -0.16
    ized
    -0.16
    cul
    -0.15
    halb
    -0.15
    icana
    -0.15
     ÄijoÃłn
    -0.15
    gang
    -0.15
    maal
    -0.15
    POSITIVE LOGITS
    etary
    0.26
    isphere
    0.22
    wright
    0.19
    ayout
    0.18
    terior
    0.18
     Parenthood
    0.18
    ter
    0.16
    stead
    0.16
    agn
    0.15
    ishing
    0.15
    Act Density 0.029%

    No Known Activations