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

    Neuronpedia

    INDEX
    Explanations

    terms related to individual roles and interactions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anker
    -0.16
    ked
    -0.14
     themselves
    -0.14
    nih
    -0.13
     massaggi
    -0.13
    weep
    -0.13
    emin
    -0.13
    cept
    -0.13
    aber
    -0.13
    eson
    -0.13
    POSITIVE LOGITS
    (s
    0.22
     himself
    0.22
     herself
    0.18
    /her
    0.18
    (es
    0.16
    oom
    0.15
    åĢij
    0.15
    们
    0.15
    ry
    0.14
    sth
    0.14
    Act Density 0.354%

    No Known Activations