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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial shares or stakes

    oai_token-act-pair · gpt-3.5-turbo

    references to shares or ownership stakes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rohing
    -0.74
     reper
    -0.70
     trance
    -0.67
     Honor
    -0.65
     skelet
    -0.60
     compr
    -0.59
    anwhile
    -0.58
     Honour
    -0.58
     simultane
    -0.57
    ensen
    -0.57
    POSITIVE LOGITS
    cro
    1.37
    holding
    1.33
    holder
    1.31
    holders
    1.20
    hold
    1.07
    fair
    0.96
    hare
    0.94
    ability
    0.94
    azo
    0.94
    ership
    0.91
    Act Density 0.041%

    No Known Activations