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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotions and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yet
    -0.27
    ä½Ĩ
    -0.25
     although
    -0.25
     though
    -0.23
    yet
    -0.22
    åį»
    -0.22
     but
    -0.22
    åį´
    -0.21
     aunque
    -0.21
    although
    -0.20
    POSITIVE LOGITS
    !!,
    0.21
    !,
    0.21
     (),
    0.19
     etc
    0.19
    %,
    0.18
     *,
    0.18
     %,
    0.18
    *,
    0.18
     ?,
    0.18
     [],
    0.17
    Act Density 0.310%

    No Known Activations