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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forms of communication and comparative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    one to one or pairwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.41
     ISTAT
    -0.40
    XmlAccessorType
    -0.40
    RTGC
    -0.39
     verwacht
    -0.39
    apunov
    -0.37
    RTEE
    -0.37
    bumps
    -0.36
     inderdaad
    -0.36
    EOUS
    -0.36
    POSITIVE LOGITS
    OneToOne
    0.54
    ManyToMany
    0.52
     direct
    0.50
     pairwise
    0.50
     directly
    0.49
     DIRECT
    0.48
     bilateral
    0.48
    直接
    0.48
     conversation
    0.48
    Personendaten
    0.44
    Act Density 0.152%

    No Known Activations