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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambi
    -0.18
    thouse
    -0.15
    \<^
    -0.15
    @brief
    -0.15
    ctp
    -0.15
    SizeMode
    -0.15
    ÑĢади
    -0.15
    .exe
    -0.15
     lastname
    -0.14
    ाà¤Ĺत
    -0.14
    POSITIVE LOGITS
     light
    0.43
     bear
    0.40
     fruition
    0.36
     life
    0.33
    bear
    0.31
     Light
    0.31
    light
    0.30
    -light
    0.30
     bare
    0.27
    Light
    0.27
    Act Density 0.040%

    No Known Activations