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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "som" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivot
    -0.17
    ignum
    -0.16
    enan
    -0.15
    amps
    -0.15
    .scalablytyped
    -0.15
    HEET
    -0.15
    eos
    -0.14
    ungs
    -0.14
    fections
    -0.14
    anga
    -0.14
    POSITIVE LOGITS
    erville
    0.28
    ewhere
    0.27
    ewhat
    0.25
    thing
    0.25
    mers
    0.23
    erset
    0.22
    brero
    0.21
    ething
    0.21
    etime
    0.21
    place
    0.18
    Act Density 0.010%

    No Known Activations