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

    Neuronpedia

    INDEX
    Explanations

    references to hills or mountainous landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kla
    -0.17
    s
    -0.16
    yne
    -0.16
    sak
    -0.16
    obra
    -0.16
    samp
    -0.15
    eos
    -0.15
    ooke
    -0.14
    olics
    -0.14
    zure
    -0.14
    POSITIVE LOGITS
    side
    0.52
    iard
    0.41
    top
    0.40
    ides
    0.32
    crest
    0.31
    arious
    0.27
    ier
    0.27
    -top
    0.22
    endale
    0.21
    borough
    0.21
    Act Density 0.010%

    No Known Activations