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

    Neuronpedia

    INDEX
    Explanations

    words related to conversion or transformation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of translation and equivalence across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Peb
    -0.82
    ndra
    -0.81
    pton
    -0.79
    odder
    -0.77
    taker
    -0.77
    luster
    -0.74
    hoff
    -0.72
    drm
    -0.72
    lain
    -0.71
    \/\/
    -0.70
    POSITIVE LOGITS
     translations
    0.95
     translate
    0.92
     translated
    0.87
     translating
    0.87
     transl
    0.87
     translates
    0.87
    ophone
    0.84
     translation
    0.81
    ãĥ¼ãĤ¯
    0.78
     interpre
    0.75
    Act Density 0.018%

    No Known Activations