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

    Neuronpedia

    INDEX
    Explanations

    references to ongoing or recurring events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :,
    -0.19
    -many
    -0.17
    must
    -0.16
    :
    -0.16
    å¿ħé¡»
    -0.14
    :[
    -0.14
    aucoup
    -0.13
     Loves
    -0.13
    (can
    -0.13
    ;
    -0.13
    POSITIVE LOGITS
     marks
    0.24
     marked
    0.20
     is
    0.17
    _marks
    0.17
    Marks
    0.17
     Marks
    0.17
    æĺ¯æĪij
    0.16
    marks
    0.16
     promises
    0.15
     was
    0.15
    Act Density 0.110%

    No Known Activations