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

    Neuronpedia

    INDEX
    Explanations

    compound adjectives and phrases that indicate specific qualities or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.34
    âĢIJ
    -0.19
    EGIN
    -0.19
    /her
    -0.18
    UGIN
    -0.17
    agua
    -0.16
    ses
    -0.16
    ặp
    -0.16
    deaux
    -0.16
    phans
    -0.15
    POSITIVE LOGITS
    /-
    0.51
    gether
    0.29
    odore
    0.26
    adays
    0.26
    atre
    0.25
    ern
    0.21
    ir
    0.21
    -turned
    0.21
    edly
    0.21
    raries
    0.20
    Act Density 1.022%

    No Known Activations