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

    Neuronpedia

    INDEX
    Explanations

    verbs denoting gaining or acquiring something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to obtaining or acquiring something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stick
    -0.66
    box
    -0.62
     Wrap
    -0.60
     Ingredients
    -0.59
    bah
    -0.59
    erb
    -0.58
    resses
    -0.58
    ordon
    -0.57
     Rod
    -0.55
    ñ
    -0.55
    POSITIVE LOGITS
     gaining
    3.32
     gained
    1.72
     obtaining
    1.70
     gain
    1.66
     attracting
    1.65
     garner
    1.63
     acquiring
    1.62
     achieving
    1.58
     becoming
    1.52
     losing
    1.47
    Act Density 0.014%

    No Known Activations