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

    Neuronpedia

    INDEX
    Explanations

    phrases about support and emotional struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beyond
    -0.17
    illet
    -0.16
    iosis
    -0.15
    yonel
    -0.15
     beyond
    -0.15
    .ManyToMany
    -0.14
    avar
    -0.14
    ocused
    -0.14
     zwar
    -0.14
    utex
    -0.14
    POSITIVE LOGITS
     nor
    0.51
    Nor
    0.36
    nor
    0.36
     Nor
    0.36
     anymore
    0.34
     NOR
    0.30
     WHATSOEVER
    0.27
     whatsoever
    0.26
     either
    0.25
     EITHER
    0.23
    Act Density 0.160%

    No Known Activations