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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of playing or having a role in a specific context or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the importance or influence of actions and roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifted
    -0.71
    pora
    -0.62
    icon
    -0.60
    identally
    -0.59
     lad
    -0.58
    utter
    -0.58
    haust
    -0.58
    ortium
    -0.57
    iflower
    -0.57
    ////////////////////////////////
    -0.56
    POSITIVE LOGITS
    wright
    1.07
    ername
    0.98
    wr
    0.83
    rored
    0.82
    lists
    0.79
     havoc
    0.74
    ulative
    0.74
    plays
    0.72
    cha
    0.69
    offs
    0.67
    Act Density 0.040%

    No Known Activations