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

    Neuronpedia

    INDEX
    Explanations

    verbs related to various types of work activities

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles related to actions conducted by various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombat
    -0.77
    ont
    -0.77
    uckle
    -0.75
    peg
    -0.72
    chini
    -0.72
    omet
    -0.72
    oxy
    -0.68
    zip
    -0.68
    omm
    -0.66
    ochond
    -0.66
    POSITIVE LOGITS
     spree
    0.69
    tons
    0.66
     fictitious
    0.64
     conduc
    0.62
    nesota
    0.60
     professions
    0.59
     Towards
    0.58
     rall
    0.57
     peanuts
    0.56
     behalf
    0.56
    Act Density 0.293%

    No Known Activations