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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or response

    oai_token-act-pair · gpt-3.5-turbo

    actions and responses that involve the word "react" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _-
    -0.70
    thing
    -0.67
     Camel
    -0.64
    esan
    -0.61
     Dome
    -0.59
    chin
    -0.59
    neath
    -0.58
    corn
    -0.58
    fo
    -0.58
    jay
    -0.57
    POSITIVE LOGITS
    ivated
    1.42
    ivating
    1.29
     negatively
    1.22
     positively
    1.21
     favorably
    1.21
    iv
    1.16
     appropriately
    1.15
     violently
    1.15
     angrily
    1.10
     harshly
    1.07
    Act Density 0.061%

    No Known Activations