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

    Neuronpedia

    INDEX
    Explanations

    themes related to survival and consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑĤвом
    -0.15
    ripp
    -0.15
    Latch
    -0.15
    _Utils
    -0.15
    iquer
    -0.14
    âĢ»
    -0.14
    ombat
    -0.14
    icut
    -0.14
     createState
    -0.13
    enguin
    -0.13
    POSITIVE LOGITS
    olo
    0.27
    lo
    0.25
    le
    0.23
    elo
    0.22
    isi
    0.21
    osi
    0.21
    sel
    0.20
    ola
    0.20
    ole
    0.19
    lesi
    0.19
    Act Density 0.012%

    No Known Activations