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

    Neuronpedia

    INDEX
    Explanations

    themes related to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iso
    -0.16
    ÙĬب
    -0.14
    Foreground
    -0.14
    urry
    -0.14
    degree
    -0.14
    ĽĦ
    -0.14
     dün
    -0.14
     Troy
    -0.13
    boro
    -0.13
     harmony
    -0.13
    POSITIVE LOGITS
     promises
    0.23
     promise
    0.21
     Promise
    0.19
    yclic
    0.16
    adem
    0.16
     promised
    0.15
    auer
    0.15
     obligations
    0.15
    Promise
    0.14
    ARA
    0.14
    Act Density 0.116%

    No Known Activations