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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms surrounding community support and safety, particularly in contexts affecting vulnerable populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLS
    -0.18
    iddy
    -0.16
    å±ħ
    -0.15
     å¸Ĥ
    -0.14
    atars
    -0.14
    URES
    -0.13
    سÙĨ
    -0.13
    anga
    -0.13
     æ
    -0.13
    retty
    -0.13
    POSITIVE LOGITS
     soon
    0.22
     forthcoming
    0.19
    soon
    0.18
     be
    0.16
     upcoming
    0.16
    fol
    0.15
    ingly
    0.15
     future
    0.15
     Soon
    0.15
    ially
    0.15
    Act Density 1.507%

    No Known Activations