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

    Neuronpedia

    INDEX
    Explanations

    the presence of citations or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     raiſ
    -0.71
     purpoſe
    -0.70
     Diſ
    -0.69
     cauſe
    -0.69
     poffe
    -0.68
     deſt
    -0.68
     pleaſure
    -0.65
     tranſ
    -0.64
    entuh
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
     al
    1.18
    __':
    0.80
     Al
    0.63
    __":
    0.62
     المعيارى
    0.60
     др
    0.56
    al
    0.55
    amazonaws
    0.54
    ernet
    0.53
     et
    0.53
    Act Density 0.107%

    No Known Activations