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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles related to actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.69
    fortunately
    -0.67
    debian
    -0.64
    dt
    -0.63
    etheless
    -0.63
    ItemTracker
    -0.62
    oche
    -0.62
     doubtless
    -0.61
    behind
    -0.60
    inger
    -0.60
    POSITIVE LOGITS
     oneself
    0.82
     Pengu
    0.66
    AME
    0.65
    HAM
    0.64
    enance
    0.63
     Souls
    0.62
     Yourself
    0.61
    ãĤ¢ãĥ«
    0.61
    AMES
    0.61
    BAT
    0.60
    Act Density 0.356%

    No Known Activations