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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal preferences and tastes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orges
    -0.16
    umba
    -0.15
    üzel
    -0.14
     ActionTypes
    -0.14
    à¤Ľ
    -0.14
     labore
    -0.14
    ripp
    -0.14
    obil
    -0.13
    rous
    -0.13
    opyright
    -0.13
    POSITIVE LOGITS
     taste
    0.74
     tastes
    0.69
     Taste
    0.56
     tasted
    0.44
     preferences
    0.42
     tast
    0.39
     вкÑĥ
    0.39
     preference
    0.37
     liking
    0.33
    preferences
    0.33
    Act Density 0.085%

    No Known Activations