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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal preferences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Possessive pronouns followed by "taste," "interest," or "liking"

    np_acts-logits-general · gemini-2.0-flash

    personal taste and liking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Isis
    -0.51
     saad
    -0.47
    WriteAttribute
    -0.47
     tule
    -0.47
    UIControlState
    -0.47
     valmis
    -0.47
    (&$
    -0.46
    diğinde
    -0.46
    duos
    -0.45
    PHS
    -0.44
    POSITIVE LOGITS
     liking
    0.93
     tastes
    0.88
     taste
    0.83
    好み
    0.81
    taste
    0.76
     interests
    0.74
     Taste
    0.73
     suit
    0.73
     preferences
    0.71
    Taste
    0.71
    Act Density 0.100%

    No Known Activations