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

    Neuronpedia

    INDEX
    Explanations

    interactions and relationships between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propositions
    -0.16
    éĽĨä¸Ń
    -0.14
     Dump
    -0.14
    endi
    -0.14
    zel
    -0.14
    ä¸İ
    -0.14
    èĪĩ
    -0.14
    deaux
    -0.14
    WP
    -0.13
     èĪ
    -0.13
    POSITIVE LOGITS
     together
    0.31
     Together
    0.27
    Together
    0.26
    ä¸Ģèµ·
    0.25
    gether
    0.23
     agreed
    0.21
     вмеÑģÑĤе
    0.20
     Agree
    0.19
     spolu
    0.19
     mutual
    0.19
    Act Density 0.244%

    No Known Activations