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

    Neuronpedia

    INDEX
    Explanations

    words related to showing concern or attention towards something

    oai_token-act-pair · gpt-3.5-turbo

    references to caring or concern for others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GV
    -0.66
    jam
    -0.65
    UES
    -0.64
    ãĥĪ
    -0.63
    antha
    -0.62
    Loading
    -0.59
    akedown
    -0.58
     Upper
    -0.57
    Assembly
    -0.56
    ãĥ³ãĤ¸
    -0.55
    POSITIVE LOGITS
     passionately
    1.17
    lessly
    1.12
     deeply
    0.98
     about
    0.94
    taker
    0.90
    lessness
    0.90
    der
    0.89
     ABOUT
    0.85
    ened
    0.81
    ately
    0.80
    Act Density 0.032%

    No Known Activations