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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and their frequency in relation to other words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olin
    -0.77
    virtual
    -0.70
    utenant
    -0.70
    assium
    -0.67
    wrap
    -0.66
    hedral
    -0.66
    holes
    -0.65
    lehem
    -0.65
    requires
    -0.65
    ernels
    -0.64
    POSITIVE LOGITS
     insistence
    1.30
     efforts
    1.29
     suggestion
    1.27
     antics
    1.25
     assertion
    1.22
     refusal
    1.20
     proposal
    1.20
     plight
    1.15
     approach
    1.15
     assertions
    1.14
    Act Density 0.106%

    No Known Activations