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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "connect" and its variations, indicating a focus on themes of connection and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loh
    -0.16
    جع
    -0.15
    icana
    -0.15
    icina
    -0.14
    aq
    -0.14
    ruba
    -0.14
    hangi
    -0.14
    oenix
    -0.14
    vrier
    -0.14
    zeug
    -0.14
    POSITIVE LOGITS
    icut
    0.26
    ivity
    0.16
    ville
    0.16
    269
    0.16
    weigh
    0.15
    point
    0.15
    IVITY
    0.14
    versations
    0.14
    we
    0.14
    s
    0.14
    Act Density 0.053%

    No Known Activations