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

    Neuronpedia

    INDEX
    Explanations

    words ending in 's'

    oai_token-act-pair · gpt-3.5-turbo

    the word "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izons
    -0.62
    irtual
    -0.62
    luaj
    -0.60
     Juda
    -0.60
    fee
    -0.59
    inav
    -0.59
    erning
    -0.58
    orthy
    -0.55
    farious
    -0.55
    icz
    -0.55
    POSITIVE LOGITS
     why
    0.92
     gonna
    0.82
     happening
    0.75
     preferable
    0.71
     okay
    0.71
     alright
    0.71
     understandable
    0.71
     impossible
    0.70
    worth
    0.69
    ername
    0.69
    Act Density 0.039%

    No Known Activations