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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate positivity or appreciation, particularly in relation to experiences or social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasi
    -0.17
    osaur
    -0.15
    ÑĢÑĥÑĪ
    -0.15
    iverz
    -0.15
    :Register
    -0.14
    ouden
    -0.14
     Structures
    -0.14
    ONGO
    -0.14
    antro
    -0.14
    áÅĻ
    -0.14
    POSITIVE LOGITS
    vens
    0.17
    ough
    0.17
    iglia
    0.15
    ey
    0.15
    oo
    0.15
     supply
    0.15
    yr
    0.15
    emark
    0.15
    --
    0.14
     itself
    0.14
    Act Density 0.025%

    No Known Activations