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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement towards a specific direction or goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases and references related to "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strives
    -0.66
     suppose
    -0.65
    iam
    -0.64
     namely
    -0.64
    iac
    -0.63
     faithfully
    -0.63
     SetFontSize
    -0.61
    thood
    -0.60
    rand
    -0.58
     worshipped
    -0.58
    POSITIVE LOGITS
     forefront
    1.24
     brink
    1.22
     depths
    1.14
     nearest
    1.09
     outskirts
    1.04
     conclusion
    1.03
     fullest
    1.01
     same
    0.97
     extent
    0.96
     lowest
    0.96
    Act Density 0.168%

    No Known Activations