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

    Neuronpedia

    INDEX
    Explanations

    expressions of goodwill or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.17
    etically
    -0.16
    ampo
    -0.15
    .backward
    -0.15
    ioc
    -0.15
    ping
    -0.14
    .ecore
    -0.14
    Gro
    -0.14
    rylic
    -0.14
    etic
    -0.14
    POSITIVE LOGITS
     да
    0.15
    -border
    0.14
    ugi
    0.14
    erah
    0.14
    _PUR
    0.14
     beg
    0.14
    ambia
    0.14
     purge
    0.13
     Weeks
    0.13
     prem
    0.13
    Act Density 0.023%

    No Known Activations