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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or difficulty in drawing conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing uncertainty or limitation in scientific conclusions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     createSprite
    -0.50
    #+#
    -0.49
    блиоте
    -0.47
    LabelTagHelper
    -0.46
    importanza
    -0.44
    reminder
    -0.43
     HasFactory
    -0.42
    Important
    -0.41
    indirect
    -0.41
    UrlResolution
    -0.41
    POSITIVE LOGITS
     definitive
    1.26
     exact
    1.19
     precise
    1.17
     definitively
    1.05
     definite
    1.02
     conclusive
    0.93
    precise
    0.93
     concrete
    0.91
    exact
    0.91
     precisely
    0.89
    Act Density 0.797%

    No Known Activations