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

    Neuronpedia

    INDEX
    Explanations

    the word "onymous" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    words related to anonymity and pseudonymity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     haste
    -0.73
    idity
    -0.67
    imm
    -0.65
    agan
    -0.65
    Sim
    -0.63
    WH
    -0.62
    pressure
    -0.62
    ERA
    -0.61
    pees
    -0.60
    HA
    -0.59
    POSITIVE LOGITS
    onymous
    1.19
    onym
    0.93
    onomous
    0.79
    named
    0.79
    ename
    0.78
    theless
    0.76
    ophers
    0.75
    uously
    0.74
    æĪ¦
    0.72
    agogue
    0.72
    Act Density 0.026%

    No Known Activations