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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and transitional phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owered
    -0.71
    %:
    -0.66
    ":[
    -0.66
    inqu
    -0.65
    icipated
    -0.65
    escription
    -0.65
    Reward
    -0.63
    ebted
    -0.62
    roup
    -0.62
    edom
    -0.61
    POSITIVE LOGITS
     incidentally
    1.31
     anyway
    1.29
     alas
    1.27
     admittedly
    1.11
    !)
    1.05
     eh
    1.03
     yes
    1.02
    *)
    1.02
     huh
    0.99
    !).
    0.99
    Act Density 0.259%

    No Known Activations