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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Bol" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to Bolivia and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.76
    dfx
    -0.71
    PLIED
    -0.66
    Alien
    -0.64
    apers
    -0.63
    abyte
    -0.62
    EY
    -0.62
     Birch
    -0.61
     EDT
    -0.61
    Bir
    -0.61
    POSITIVE LOGITS
    ivia
    0.91
    zar
    0.83
    ign
    0.82
    acas
    0.79
    uca
    0.79
    idays
    0.78
    ength
    0.78
    oning
    0.76
    atility
    0.75
    olic
    0.75
    Act Density 0.025%

    No Known Activations