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

    Neuronpedia

    INDEX
    Explanations

    sentences that commend work or efforts, particularly those describing jobs well done

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows pronouns or determiners

    np_acts-logits-general · gemini-2.0-flash

    a great job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.67
     Steep
    -0.60
     Rady
    -0.60
    "}")
    -0.59
    hdashline
    -0.59
    urlpatterns
    -0.57
     Pingback
    -0.57
    stateProvider
    -0.57
    Diwedd
    -0.56
    ագրություններ
    -0.55
    POSITIVE LOGITS
     job
    0.67
    queryInterface
    0.59
     damage
    0.58
     work
    0.56
     done
    0.55
     Damage
    0.54
     CascadeType
    0.53
    omitempty
    0.53
    effectuer
    0.52
     deed
    0.51
    Act Density 0.160%

    No Known Activations