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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and descriptors related to reactions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    archy
    -0.17
    emption
    -0.14
    licate
    -0.14
    opper
    -0.14
     Uns
    -0.14
    微软éĽħé»ij
    -0.13
     Interr
    -0.13
    оÑīи
    -0.13
    kl
    -0.13
    .squareup
    -0.13
    POSITIVE LOGITS
    izing
    0.64
    ising
    0.59
    ifying
    0.56
    ating
    0.52
    ening
    0.50
    ingly
    0.50
    ing
    0.48
    iating
    0.48
    ting
    0.47
    ulating
    0.47
    Act Density 0.102%

    No Known Activations